© 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. 40993
    Prev
    Next
    INDEX
    Explanations

    free downloads and high expectations

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

    vapor upwards, liquid downwards

    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
     नवरा
    0.48
    стве
    0.47
    ما
    0.47
    c
    0.46
    кана
    0.46
    xanth
    0.45
     casts
    0.45
    எம்
    0.44
     भला
    0.44
    年末
    0.44
    POSITIVE LOGITS
     উঠিয়া
    0.47
     personalità
    0.44
    ;";
    0.44
    padding
    0.43
    ہوری
    0.42
     pah
    0.42
     möglicherweise
    0.42
     ঘুম
    0.41
     потря
    0.41
    ujete
    0.41
    Activations Density 0.000%

    No Known Activations