© 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. 164053
    Prev
    Next
    INDEX
    Explanations

    purpose, goals, and products

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

    beliefs, broken, vertical, technology, equipped, exploring, set

    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
    ке
    0.56
    ン
    0.54
    텐
    0.47
    н
    0.47
    回転
    0.46
    嗕
    0.46
     faded
    0.45
    ګه
    0.45
     turns
    0.44
    ೀ
    0.44
    POSITIVE LOGITS
    panel
    0.50
    Ion
    0.49
    বাদে
    0.48
    ningen
    0.48
     Pann
    0.48
     종류
    0.48
     Int
    0.47
     దాని
    0.46
     Suez
    0.46
     Gamb
    0.46
    Activations Density 0.000%

    No Known Activations