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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8741
    Prev
    Next
    INDEX
    Explanations

    language and code structure

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

    The neuron flags unusually long tokens (i.e. multi-syllable or multi-character words/subwords).

    oai_token-act-pair · o4-miniTriggered 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
    ,
    0.86
    ,__
    0.78
     lubricating
    0.76
     संबद्ध
    0.74
    Cindy
    0.74
     Cindy
    0.73
    ceres
    0.73
     electronically
    0.72
    GroupLayout
    0.70
     absorbance
    0.70
    POSITIVE LOGITS
    PROOF
    0.72
    د
    0.72
    ленно
    0.71
     فار
    0.71
     dites
    0.70
     акчага
    0.70
     قتل
    0.68
     عوامل
    0.68
     swept
    0.68
     نز
    0.67
    Activations Density 0.000%

    No Known Activations