© 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. 148369
    Prev
    Next
    INDEX
    Explanations

    access to conservatories

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

    categories followed by colon

    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
     açısından
    0.48
    Dequeue
    0.47
    ือ
    0.46
    AMENTO
    0.46
    createSprite
    0.44
    녘
    0.43
    жливо
    0.43
     jsonify
    0.43
    ით
    0.43
    ֹ
    0.42
    POSITIVE LOGITS
     جائزے
    0.55
     रसायन
    0.53
     Pine
    0.48
     எண்
    0.48
     ده
    0.47
     Crimson
    0.47
     Microsoft
    0.46
     Pháp
    0.46
     প্রবন্ধে
    0.46
     प्रार्थ
    0.45
    Activations Density 0.001%

    No Known Activations