© 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. 78902
    Prev
    Next
    INDEX
    Explanations

    fails to

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

    potential benefits

    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
    Ś
    0.48
    łoż
    0.46
     অত্যাচার
    0.46
    ณ์
    0.46
    口感
    0.45
    هِ
    0.45
    ברה
    0.44
     ইউরোপ
    0.44
     यंत्र
    0.44
     Biochim
    0.43
    POSITIVE LOGITS
    u
    0.63
    ik
    0.56
     {
    0.52
     tán
    0.51
    untamiento
    0.51
    ibouti
    0.50
     misa
    0.49
    }{
    0.47
     destacó
    0.47
    asic
    0.47
    Activations Density 0.001%

    No Known Activations