© 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. 105387
    Prev
    Next
    INDEX
    Explanations

    in keeping with

    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
    𓋼
    -1.98
     skvě
    -1.97
    靦
    -1.84
     szczeg
    -1.80
     úspě
    -1.75
    </strong>
    -1.74
    ツイッター
    -1.73
    驟
    -1.71
     sprzedaży
    -1.70
     zajíma
    -1.69
    POSITIVE LOGITS
    ;
    2.06
     juntamente
    1.80
    n
    1.73
     nebst
    1.63
    8
    1.60
    na
    1.55
    。
    1.54
    全都
    1.51
    5
    1.50
    程度上
    1.47
    Activations Density 0.006%

    No Known Activations