© 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. 78158
    Prev
    Next
    INDEX
    Explanations

    run wild, runaway, amok

    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
    <0x94>
    -0.81
    ність
    -0.75
     ingreso
    -0.75
    esi
    -0.71
    imiento
    -0.71
    ᥣ
    -0.71
    ón
    -0.69
    snapshot
    -0.69
     אל
    -0.69
    แม่
    -0.69
    POSITIVE LOGITS
     run
    3.56
     runaway
    3.53
     Run
    2.80
    Run
    2.72
    run
    2.69
     ran
    2.38
     rampant
    2.20
     wild
    2.20
     RUN
    2.19
    RUN
    2.13
    Activations Density 0.059%

    No Known Activations