© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70041
    Prev
    Next
    INDEX
    Explanations

    physical harm

    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
    罰
    -0.77
     pestil
    -0.76
    種類
    -0.75
     Draws
    -0.75
     registers
    -0.74
     incidencia
    -0.73
     massacres
    -0.72
     arenas
    -0.71
     discharged
    -0.71
     deseo
    -0.70
    POSITIVE LOGITS
     injuries
    3.53
     Injuries
    2.33
    Injuries
    2.02
     wounds
    1.78
    juries
    1.61
     injury
    1.35
     blessures
    1.21
     lesiones
    1.14
    injury
    1.11
     multiple
    1.08
    Activations Density 0.032%

    No Known Activations