© 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. 34-GEMMASCOPE-RES-131K
    7. 3287
    Prev
    Next
    INDEX
    Explanations

    punches, hits, attacks

    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_34/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
    aconda
    -0.85
    Fragments
    -0.83
    ›
    -0.82
     uur
    -0.78
    argout
    -0.77
    rant
    -0.77
     symmetries
    -0.77
     donnent
    -0.76
    簷
    -0.76
    ㅈ
    -0.75
    POSITIVE LOGITS
     attacks
    1.84
     physical
    1.24
     ataques
    1.20
    Attacks
    1.18
     getting
    1.16
     attack
    1.14
     hits
    1.13
     received
    1.10
    attacks
    1.09
     punches
    1.07
    Activations Density 0.018%

    No Known Activations