© 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. 10-GEMMASCOPE-RES-131K
    7. 100780
    Prev
    Next
    INDEX
    Explanations

    shot or wounded people

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

    descriptions of injuries, wounds, or violence involving people being hurt.

    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_10/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
    ées
    -1.40
     forbin
    -1.34
    fahan
    -1.31
     milj
    -1.29
     pourquoi
    -1.27
     visiter
    -1.25
    และ
    -1.23
     bottes
    -1.23
    htë
    -1.22
     geel
    -1.22
    POSITIVE LOGITS
     with
    1.40
     partially
    1.32
     will
    1.26
     during
    1.23
     like
    1.21
     as
    1.21
     такими
    1.19
     highlighted
    1.17
     while
    1.16
     makes
    1.16
    Activations Density 0.038%

    No Known Activations