© 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. 177279
    Prev
    Next
    INDEX
    Explanations

    state abbreviations and history

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

    characteristics with fascism

    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
    metre
    0.53
     undoubt
    0.51
     unfore
    0.48
     マスター
    0.48
    <unused430>
    0.45
     บุ
    0.45
     inconce
    0.45
    master
    0.44
     전류
    0.44
     промы
    0.43
    POSITIVE LOGITS
    History
    0.52
     Historic
    0.52
    For
    0.51
    Account
    0.51
    ే
    0.51
    帐
    0.49
    Historic
    0.49
    Hello
    0.49
    Bishop
    0.48
    История
    0.48
    Activations Density 0.000%

    No Known Activations