© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 816
    Prev
    Next
    INDEX
    Explanations

    html doctype declarations

    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_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
     '
    -1.98
    了很多
    -1.77
    _
    -1.66
     "
    -1.58
    是一个
    -1.55
    INGREDIENT
    -1.53
     stalwart
    -1.52
     Instead
    -1.52
     beiden
    -1.51
     paltry
    -1.49
    POSITIVE LOGITS
     that
    1.77
    ığında
    1.68
     "}";
    1.66
     Į
    1.64
    انا
    1.59
     lesquelles
    1.56
     prace
    1.56
    餮
    1.55
    ''',
    1.55
     onlyOwner
    1.55
    Activations Density 0.017%

    No Known Activations