© 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. 7458
    Prev
    Next
    INDEX
    Explanations

    escape punishment, traditional research, generator, small intestinal

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

    content that appears to be spam, automatically generated text, or HTML/code fragments.

    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
     dianteira
    -1.67
     الحالي
    -1.65
     and
    -1.65
     ventilación
    -1.59
     of
    -1.55
     satılık
    -1.55
    ætte
    -1.52
    áles
    -1.48
     flexibilidad
    -1.47
    的模样
    -1.45
    POSITIVE LOGITS
     other
    2.02
     in
    1.47
     дуже
    1.45
     Sometimes
    1.45
     popolo
    1.44
    ఫ
    1.43
    ड
    1.41
    У
    1.38
     amorosa
    1.36
    oides
    1.35
    Activations Density 0.002%

    No Known Activations