© 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. 123837
    Prev
    Next
    INDEX
    Explanations

    congratulations on your

    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
     you
    -2.33
     people
    -2.17
    <h2>
    -1.94
     allow
    -1.87
     if
    -1.84
    If
    -1.83
    <h3>
    -1.79
    ization
    -1.75
     need
    -1.71
     или
    -1.70
    POSITIVE LOGITS
     ventes
    1.77
    loggen
    1.77
    螄
    1.75
     edelstahl
    1.74
    ㌧
    1.73
    盉
    1.70
    ėjo
    1.68
     melden
    1.66
    malige
    1.66
    蚰
    1.63
    Activations Density 0.004%

    No Known Activations