© 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. 29199
    Prev
    Next
    INDEX
    Explanations

    location of things

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

    hormonal influence on muscle and strength

    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
    ਕ
    0.54
    زا
    0.47
    zł
    0.46
    izons
    0.46
    ività
    0.44
    ک
    0.44
    レ
    0.44
     monies
    0.44
     iced
    0.43
     licenci
    0.43
    POSITIVE LOGITS
     renounce
    0.55
     動画
    0.47
     রায়
    0.45
     губерна
    0.44
     పార్
    0.43
    foot
    0.43
    }>
    0.43
    simulate
    0.43
     متحدہ
    0.42
     قاعده
    0.42
    Activations Density 0.000%

    No Known Activations