© 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. 37676
    Prev
    Next
    INDEX
    Explanations

    proposal acceptance

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

    truth-teller and liar situations

    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
    lera
    0.47
    t
    0.45
     I
    0.44
    tochrome
    0.43
     and
    0.42
     Carole
    0.40
    -//
    0.40
    lana
    0.39
     Piero
    0.39
     Loop
    0.39
    POSITIVE LOGITS
     основним
    0.55
    جار
    0.54
     필
    0.51
    !}{
    0.50
    ਕੇ
    0.47
     чаще
    0.46
    Fill
    0.46
    мор
    0.46
    isser
    0.45
     општи
    0.45
    Activations Density 0.000%

    No Known Activations