© 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. 89165
    Prev
    Next
    INDEX
    Explanations

    cached credentials

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

    reconnaissance

    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
     to
    0.60
    i
    0.53
     tacky
    0.51
    ي
    0.50
     transmutation
    0.47
     तरीके
    0.47
     ultrasonic
    0.46
    崦
    0.46
     transcend
    0.45
     transcendent
    0.45
    POSITIVE LOGITS
    ্তির
    0.55
    rinho
    0.49
    DataType
    0.49
    Dani
    0.49
    ozat
    0.47
    strcmp
    0.46
    Lem
    0.46
    ETE
    0.46
    Cookie
    0.45
    Camping
    0.45
    Activations Density 0.000%

    No Known Activations