© 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. 1122
    Prev
    Next
    INDEX
    Explanations

    Q: questions, In vitro, Summer, Getting

    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
    狴
    -1.75
     cadáver
    -1.73
     ontdek
    -1.72
     tne
    -1.68
    hance
    -1.67
    罴
    -1.64
    bringen
    -1.63
     碗
    -1.61
     اللہ
    -1.61
    CREDIT
    -1.59
    POSITIVE LOGITS
    section
    2.25
    ft
    2.08
    ),
    1.99
    also
    1.90
    begin
    1.87
    RE
    1.84
    derdag
    1.82
    2
    1.77
    AS
    1.76
    chengladbach
    1.75
    Activations Density 0.000%

    No Known Activations