© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6035
    Prev
    Next
    INDEX
    Explanations

    In function or this

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

    The neuron is detecting numeric values with decimal points (floating‐point numbers).

    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_31_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
    當
    0.66
     Fraction
    0.64
    இது
    0.60
    Το
    0.58
     cela
    0.57
     Comunic
    0.57
    最近
    0.57
     Infected
    0.56
     Pint
    0.56
     最近
    0.56
    POSITIVE LOGITS
    懶
    0.71
     schlim
    0.60
    懒
    0.57
     sortBy
    0.55
    лма
    0.55
    rowset
    0.55
    өр
    0.55
     ferramentas
    0.55
    jsonwebtoken
    0.54
     minimalist
    0.53
    Activations Density 0.001%

    No Known Activations