© 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. 11481
    Prev
    Next
    INDEX
    Explanations

    De Niro / Daenerys

    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
    </strong>
    -3.75
    </h3>
    -2.08
    .”
    -2.03
     Verfasser
    -1.99
    vať
    -1.98
     assuring
    -1.95
     eigenes
    -1.95
     Некоторые
    -1.93
    vegli
    -1.91
    蕺
    -1.90
    POSITIVE LOGITS
    ing
    2.41
    le
    2.39
    蟶
    1.92
    -
    1.89
    🔥🔥
    1.86
     Kredit
    1.82
     ausein
    1.80
    ut
    1.75
    ;
    1.71
    人を
    1.71
    Activations Density 0.036%

    No Known Activations