© 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. 34975
    Prev
    Next
    INDEX
    Explanations

    questions followed by comma or complaints

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

    detailed descriptions

    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
    ↵
    0.58
     quay
    0.55
     {
    0.54
     an
    0.54
     RC
    0.52
     DC
    0.51
    /
    0.51
     Mr
    0.50
     FI
    0.49
     a
    0.49
    POSITIVE LOGITS
     большой
    0.54
    kadang
    0.54
     форме
    0.53
    glichen
    0.52
    شود
    0.52
    illaume
    0.52
    चलिए
    0.51
    iformis
    0.51
    andaag
    0.50
    ipients
    0.50
    Activations Density 0.000%

    No Known Activations