© 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. 22-GEMMASCOPE-RES-131K
    7. 34055
    Prev
    Next
    INDEX
    Explanations

    unique presentation of facial musculature

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

    punctuation marks followed by structured text elements, especially in academic or technical documents.

    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_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
    Large
    -0.76
     C
    -0.75
     START
    -0.75
     CA
    -0.74
     min
    -0.73
     goal
    -0.73
    minim
    -0.71
    恺
    -0.71
     CE
    -0.71
     hel
    -0.71
    POSITIVE LOGITS
    umque
    0.90
     pnl
    0.89
     extérieurs
    0.86
     fiore
    0.85
     대해
    0.84
    Termine
    0.84
     perintah
    0.84
     lunghe
    0.84
    Planta
    0.83
    subTitle
    0.82
    Activations Density 0.053%

    No Known Activations