© 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. 57406
    Prev
    Next
    INDEX
    Explanations

    burst or bust

    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
     Temperatur
    -0.79
    น้อย
    -0.78
    goire
    -0.78
     Го
    -0.76
    setVisibility
    -0.75
    ien
    -0.75
     Қ
    -0.71
     PATENT
    -0.71
     familial
    -0.71
    quirer
    -0.71
    POSITIVE LOGITS
     Bust
    1.14
    Bust
    0.96
     bust
    0.94
    bust
    0.88
     Trusted
    0.81
     busts
    0.80
     Rhymes
    0.79
     chỉ
    0.78
     appendix
    0.78
     bustling
    0.77
    Activations Density 0.017%

    No Known Activations