© 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. 41-GEMMASCOPE-2-RES-65K
    7. 14143
    Prev
    Next
    INDEX
    Explanations

    code or numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    ंदरे
    0.59
     aceptar
    0.58
    》(
    0.57
     domani
    0.54
    വന്‍
    0.54
    ”(
    0.54
     promover
    0.53
    𝜁
    0.53
     promouvoir
    0.52
    接受
    0.51
    POSITIVE LOGITS
    enclose
    0.75
     underline
    0.74
    .___
    0.72
    underline
    0.68
     \\
    0.68
    ____
    0.67
    ___
    0.66
    \,\
    0.65
     ___
    0.64
    \\\
    0.64
    Activations Density 0.006%

    No Known Activations