© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119984
    Prev
    Next
    INDEX
    Explanations

    Bank Street

    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
     Commencez
    -1.68
    räck
    -1.61
    ciąż
    -1.48
     âges
    -1.48
    foque
    -1.47
     ontdek
    -1.47
    ⇹
    -1.47
     alasan
    -1.45
     étages
    -1.44
     Abonnez
    -1.43
    POSITIVE LOGITS
    k
    1.87
    li
    1.77
    g
    1.55
    Pengertian
    1.55
    na
    1.52
    h
    1.50
    蛧
    1.47
    j
    1.45
    le
    1.42
     практически
    1.42
    Activations Density 10.558%

    No Known Activations