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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118745
    Prev
    Next
    INDEX
    Explanations

    victims of violence and crime

    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
    nhung
    -0.77
    arim
    -0.74
    েক
    -0.72
     lifter
    -0.72
    してみてください
    -0.71
    Réponse
    -0.68
    Eqn
    -0.68
     raiders
    -0.68
     Verlust
    -0.68
     demselben
    -0.68
    POSITIVE LOGITS
     victims
    6.53
     victim
    6.28
    victim
    4.75
     Victims
    4.47
     Victim
    4.19
     víctimas
    3.84
    Victim
    3.81
     жерт
    3.80
     victime
    3.73
     víctima
    3.69
    Activations Density 0.112%

    No Known Activations