© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1495
    Prev
    Next
    INDEX
    Explanations

    retrieve a list

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of decimal numbers (i.e. floating‐point numeric values) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numeric values embedded within structured technical or legal text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    academic-style references and technical numeric notation, such as citations, section numbering, and measurement figures.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Appeal
    0.55
     裏
    0.53
     Nguyên
    0.52
     Khánh
    0.52
     Snacks
    0.52
     Trish
    0.51
     fondly
    0.50
     Glam
    0.49
     Spezial
    0.49
     અન્ય
    0.49
    POSITIVE LOGITS
     transmembrane
    0.45
     microtub
    0.43
     paciente
    0.42
    患者
    0.41
     polynucle
    0.40
     histologic
    0.40
     injective
    0.39
     откло
    0.38
     grafo
    0.38
     subnet
    0.38
    Activations Density 0.001%

    No Known Activations