© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34215
    Prev
    Next
    INDEX
    Explanations

    attack and strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Wander
    -1.21
    强制
    -1.19
    unuz
    -1.19
    贗
    -1.16
     excessive
    -1.16
    Y
    -1.14
    when
    -1.13
    landır
    -1.12
     Eleg
    -1.11
    laşı
    -1.11
    POSITIVE LOGITS
     against
    1.93
     moves
    1.56
     strategy
    1.53
     vectors
    1.46
    撂
    1.45
     💪
    1.44
     attacks
    1.43
     attack
    1.41
    vccd
    1.40
    嬉しいです
    1.39
    Activations Density 0.048%

    No Known Activations