© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71474
    Prev
    Next
    INDEX
    Explanations

    titles followed by names

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

    development and stopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     nerve
    0.51
     neurological
    0.46
    ُوْ
    0.45
     nervous
    0.43
    कांच्या
    0.43
     mammary
    0.43
    聞いた
    0.42
     Neurology
    0.42
    ỏa
    0.42
     handwriting
    0.41
    POSITIVE LOGITS
    t
    0.51
     cóm
    0.48
    finaly
    0.47
    $(\
    0.46
     etkin
    0.46
    ប្រតិ
    0.46
    inky
    0.46
     உதவிய
    0.45
     stö
    0.45
    create
    0.45
    Activations Density 0.001%

    No Known Activations