© 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. 45105
    Prev
    Next
    INDEX
    Explanations

    unique

    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
    ↵↵
    -3.22
    ";
    -2.61
     terrific
    -2.47
    mathrm
    -2.47
    ’
    -2.41
     '
    -2.30
    >
    -2.30
     delightfully
    -2.25
                  
    -2.19
    {
    -2.19
    POSITIVE LOGITS
    璈
    2.69
    䉴
    2.67
     makes
    2.59
    just
    2.58
    Several
    2.50
     heartfelt
    2.48
    because
    2.47
     seems
    2.45
    »،
    2.45
    There
    2.38
    Activations Density 0.011%

    No Known Activations