© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40992
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     查询
    0.61
    getRedTeam
    0.57
    getBlueTeam
    0.55
     പറയുന്നത്
    0.50
    getPrototypeOf
    0.49
     或
    0.49
     メール
    0.49
     அடுத்து
    0.48
     instructive
    0.48
     popOperand
    0.48
    POSITIVE LOGITS
    OK
    0.51
    :|
    0.47
    AI
    0.45
    Er
    0.44
     direction
    0.42
    B
    0.41
    اح
    0.41
    ,
    0.41
    API
    0.40
    ON
    0.40
    Activations Density 0.004%

    No Known Activations