© 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. 68892
    Prev
    Next
    INDEX
    Explanations

    recieving end

    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
     “
    -2.14
     is
    -1.95
    }.
    -1.95
    ”;
    -1.86
    ”.
    -1.77
    ”:
    -1.69
    dáms
    -1.68
    fastjson
    -1.67
    荦
    -1.66
    鲆
    -1.66
    POSITIVE LOGITS
    !"
    1.83
    re
    1.80
     "
    1.70
    就像是
    1.68
     '
    1.54
     THEY
    1.50
    —
    1.49
    There
    1.48
    ––
    1.47
     tuviera
    1.45
    Activations Density 0.045%

    No Known Activations