© 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. 157664
    Prev
    Next
    INDEX
    Explanations

    inspiration from, photo, race, Unity propagand

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

    primary function

    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
    𝚔
    0.48
    膠
    0.47
    𝗴
    0.46
     blancas
    0.46
     mèo
    0.46
    ciencia
    0.45
    getBlueTeam
    0.45
    𝙢
    0.45
    CROSS
    0.44
    TEAM
    0.43
    POSITIVE LOGITS
    ↵↵
    0.48
    ่
    0.47
     elim
    0.46
     lanjutan
    0.45
     illet
    0.44
     */
    0.44
     theorem
    0.44
     we
    0.43
     equating
    0.43
    </blockquote>
    0.43
    Activations Density 0.001%

    No Known Activations