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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117088
    Prev
    Next
    INDEX
    Explanations

    body part injuries

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions of physical injuries and bodily trauma.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ソング
    -0.86
     INSTANCE
    -0.85
     होने
    -0.83
    PROBLEM
    -0.82
    ズル
    -0.81
     PROBLEM
    -0.80
     unending
    -0.78
     cereales
    -0.77
     anymore
    -0.77
    masalah
    -0.76
    POSITIVE LOGITS
     three
    1.08
     both
    1.07
     Both
    1.02
    Both
    1.01
     BOTH
    0.93
    پرس
    0.91
    右
    0.90
     ieg
    0.90
    läufe
    0.87
     right
    0.87
    Activations Density 0.032%

    No Known Activations