© 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. 248291
    Prev
    Next
    INDEX
    Explanations

    year Anniversary Party

    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
    W
    0.50
    WW
    0.46
    BLE
    0.46
    ುತ್ತದೆ
    0.45
    BP
    0.45
    ất
    0.44
    UM
    0.43
    UNCH
    0.43
    AGRAM
    0.43
    Hik
    0.42
    POSITIVE LOGITS
     Nullam
    0.50
    लेली
    0.44
    ヶ月
    0.43
     textil
    0.43
     ትንሽ
    0.43
    帰
    0.43
    牷
    0.43
     Pikachu
    0.42
     Joss
    0.42
    シル
    0.42
    Activations Density 0.001%

    No Known Activations