© 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. 22-GEMMASCOPE-RES-131K
    7. 67396
    Prev
    Next
    INDEX
    Explanations

    standoff, danger, confrontation, risk

    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_22/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
     ویتامین
    -1.06
     to
    -1.03
    $
    -0.98
     $
    -0.98
     these
    -0.97
     årene
    -0.95
    pośred
    -0.91
     for
    -0.91
     minhas
    -0.90
     Chaque
    -0.87
    POSITIVE LOGITS
     dangerous
    1.40
     danger
    1.21
     risks
    1.09
     خطر
    1.07
     risky
    1.06
    URIDAD
    1.05
     safety
    1.05
     configuration
    1.04
     risk
    1.04
     negotiations
    1.03
    Activations Density 0.029%

    No Known Activations