© 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. 30685
    Prev
    Next
    INDEX
    Explanations

    agency operations

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

    key instruction or condition

    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
    existence
    0.49
     Existence
    0.47
    Termination
    0.46
    𝗖
    0.46
     سلو
    0.45
    डे
    0.45
    બો
    0.45
    ДЕ
    0.45
     Taal
    0.45
     Damien
    0.44
    POSITIVE LOGITS
    );
    0.53
     anivers
    0.49
     senate
    0.49
     sân
    0.48
     baik
    0.47
    yectos
    0.46
     when
    0.45
     preserves
    0.45
    ),
    0.45
     mivel
    0.45
    Activations Density 0.000%

    No Known Activations