© 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. 165923
    Prev
    Next
    INDEX
    Explanations

    food centre

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

    badges earned, growing movement

    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
     معي
    0.43
    液晶
    0.42
     андроид
    0.42
    eventId
    0.41
    主机
    0.40
    autoconfigure
    0.40
    اكم
    0.40
    <0xCE>
    0.40
     জেল
    0.39
     ooit
    0.39
    POSITIVE LOGITS
    Yoga
    0.53
     duch
    0.48
    Todas
    0.48
    Muchas
    0.48
    Everyone
    0.46
     вопроса
    0.46
    San
    0.46
     Regl
    0.46
     इनोवेशन
    0.46
    Después
    0.45
    Activations Density 0.000%

    No Known Activations