© 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. 63698
    Prev
    Next
    INDEX
    Explanations

    injury reporting

    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
    iciaries
    -0.77
     Vengeance
    -0.75
    麩
    -0.73
    "#
    -0.72
    Équipe
    -0.71
     individuo
    -0.69
    mfenced
    -0.69
     Meadows
    -0.69
     galaxia
    -0.67
    achat
    -0.67
    POSITIVE LOGITS
     injuries
    1.67
     injury
    1.65
     lost
    1.58
     Lost
    1.47
    Lost
    1.36
    injury
    1.36
     Injuries
    1.30
     Injury
    1.28
     incident
    1.23
     incidents
    1.20
    Activations Density 0.026%

    No Known Activations