© 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. 146288
    Prev
    Next
    INDEX
    Explanations

    generation born

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

    return and defined

    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
    ρική
    0.49
    ።
    0.49
     Kentucky
    0.47
    荠
    0.47
    萵
    0.46
     WRITE
    0.46
    篑
    0.46
     języ
    0.45
    艨
    0.45
     Министерство
    0.45
    POSITIVE LOGITS
    queda
    0.49
     கொண்டிருந்த
    0.46
    aksha
    0.45
    esson
    0.44
     pudo
    0.44
    ියේ
    0.43
    handedly
    0.43
    ága
    0.43
    ämä
    0.42
     comforting
    0.42
    Activations Density 0.001%

    No Known Activations