© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1508
    Prev
    Next
    INDEX
    Explanations

    kickoff timing

    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
     جشنواره
    -0.80
     anuncia
    -0.70
    zeczytaj
    -0.68
    ]`
    -0.67
     końca
    -0.66
     bay
    -0.66
    +```
    -0.66
     Joh
    -0.66
     reli
    -0.65
    blender
    -0.65
    POSITIVE LOGITS
     kick
    4.56
     kickoff
    4.25
    Kick
    3.97
     Kick
    3.95
    kick
    3.75
    キック
    2.92
     KICK
    2.84
     kicks
    2.73
     kicked
    2.66
     kicking
    2.36
    Activations Density 0.044%

    No Known Activations