© 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. 109814
    Prev
    Next
    INDEX
    Explanations

    freak creep geek peek

    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
    complexType
    -0.82
    attere
    -0.81
    pinephrine
    -0.78
    的下
    -0.78
    IBM
    -0.73
     secciones
    -0.73
     kooper
    -0.72
     Sitzung
    -0.71
    President
    -0.71
    ¼
    -0.71
    POSITIVE LOGITS
     freak
    1.08
    freak
    1.02
     Freak
    0.98
    show
    0.97
    Freak
    0.94
    Creep
    0.88
     Creep
    0.85
    TableViewCell
    0.84
     PriorityQueue
    0.81
    QJ
    0.81
    Activations Density 0.020%

    No Known Activations