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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118486
    Prev
    Next
    INDEX
    Explanations

    reviewing content

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     shipyard
    -0.73
     الشرق
    -0.69
    TextAlign
    -0.69
     Winfrey
    -0.65
    ギャ
    -0.64
     tabled
    -0.64
     sun
    -0.63
     панели
    -0.63
     hieronder
    -0.63
    ]),
    -0.62
    POSITIVE LOGITS
     review
    2.86
    review
    2.67
     reviewing
    2.47
    Review
    2.31
     reviewed
    2.28
     reviews
    2.28
     Review
    2.28
     REVIEW
    2.16
    REVIEW
    2.14
    reviews
    1.92
    Activations Density 0.018%

    No Known Activations