© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40992
    Prev
    Next
    INDEX
    Explanations

    a process

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

    spellcasting, vulnerability scanning

    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
     查询
    0.58
    getRedTeam
    0.53
     メール
    0.52
     读取
    0.49
     фа
    0.48
     осіб
    0.47
    dispatchEvent
    0.47
     或
    0.47
     видно
    0.47
    getPrototypeOf
    0.46
    POSITIVE LOGITS
    :|
    0.52
    OK
    0.49
    API
    0.44
     direction
    0.43
    BI
    0.43
    AI
    0.43
    Er
    0.43
    يرا
    0.42
    لي
    0.42
    اح
    0.42
    Activations Density 0.000%

    No Known Activations