© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40511
    Prev
    Next
    INDEX
    Explanations

    Texas, Austin, city officials

    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
     Having
    -1.71
     Using
    -1.69
     Despite
    -1.56
    stości
    -1.55
     However
    -1.50
    ieuses
    -1.50
     Providing
    -1.47
    Ironically
    -1.45
    ânico
    -1.45
     Although
    -1.44
    POSITIVE LOGITS
    ’
    1.85
    ふたり
    1.54
    でない
    1.45
    ."
    1.45
    \_
    1.45
     ancora
    1.43
    部分を
    1.43
     vijf
    1.43
     "
    1.41
    はこの
    1.41
    Activations Density 0.007%

    No Known Activations