© 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. 20896
    Prev
    Next
    INDEX
    Explanations

    HTML entities and special characters

    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
     और
    -2.06
    quelize
    -1.91
     what
    -1.86
     where
    -1.86
    am
    -1.81
    k
    -1.78
    la
    -1.77
    carian
    -1.76
     not
    -1.70
    },
    -1.70
    POSITIVE LOGITS
    erializer
    2.14
    向けの
    2.11
    になっています
    2.09
    ichteten
    2.08
    pisah
    2.08
    튿
    2.03
    聼
    2.03
    wachen
    2.00
    ichtete
    1.95
    niająca
    1.93
    Activations Density 0.029%

    No Known Activations