© 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. 118795
    Prev
    Next
    INDEX
    Explanations

    cutthroat world

    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
    vgili
    -0.91
    ']
    -0.90
    PostInfinity
    -0.88
     påvir
    -0.88
    étrie
    -0.87
    pozdrawiam
    -0.86
     szeptember
    -0.85
    Orts
    -0.85
     okuyayım
    -0.84
    į
    -0.84
    POSITIVE LOGITS
     ruth
    1.71
     ruthless
    1.70
    ruth
    1.39
     aggressive
    1.35
    survival
    1.23
    Aggressive
    1.22
     competitive
    1.20
     unscrupulous
    1.20
     Aggressive
    1.18
     survival
    1.17
    Activations Density 0.041%

    No Known Activations