© 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. 143533
    Prev
    Next
    INDEX
    Explanations

    books and stories

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

    Okay, response structure

    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
     Schulz
    0.53
     procedimento
    0.51
    готовка
    0.47
     Helmut
    0.47
     siglas
    0.46
    0.46
    -
    0.46
     com
    0.45
     logrado
    0.45
     rapp
    0.44
    POSITIVE LOGITS
    ޘ
    0.52
    kec
    0.51
     ٹ
    0.48
    iec
    0.47
    .",[
    0.46
    urkan
    0.46
    as
    0.46
    .”[
    0.46
    getDouble
    0.46
    ".[
    0.46
    Activations Density 0.000%

    No Known Activations