© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44172
    Prev
    Next
    INDEX
    Explanations

    toxic effects and substances

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

    words and phrases related to toxicity, particularly in scientific/medical contexts.

    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
    </sub>
    -2.19
    </h3>
    -2.05
    (
    -1.96
    '
    -1.92
    drawSprites
    -1.83
    I
    -1.81
    h
    -1.80
     friv
    -1.80
    You
    -1.75
    </i>
    -1.72
    POSITIVE LOGITS
     Utiliza
    1.95
     erwähnten
    1.84
     писать
    1.80
     Nunca
    1.77
    行きます
    1.75
     That
    1.75
     Simplemente
    1.70
    扪
    1.70
     Aseg
    1.70
    mployment
    1.67
    Activations Density 0.076%

    No Known Activations