© 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. 105018
    Prev
    Next
    INDEX
    Explanations

    he will

    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
    şık
    -1.80
    waniem
    -1.77
    ą
    -1.74
     عزیز
    -1.73
    entrion
    -1.66
    aknya
    -1.55
     quotidienne
    -1.52
    目的是
    -1.52
    摭
    -1.51
     Instead
    -1.50
    POSITIVE LOGITS
     was
    1.74
    逦
    1.63
     only
    1.61
     of
    1.57
    this
    1.55
     also
    1.53
     escritório
    1.50
     такого
    1.47
     neither
    1.46
     never
    1.41
    Activations Density 0.033%

    No Known Activations