© 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. 1431
    Prev
    Next
    INDEX
    Explanations

    bind

    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
    e
    -3.52
    k
    -3.11
    ing
    -2.83
    if
    -2.48
    as
    -2.42
    er
    -2.33
    ))}
    -2.33
    鲼
    -2.31
    begin
    -2.28
    ee
    -2.27
    POSITIVE LOGITS
    ineſs
    2.92
    勦
    2.70
    盦
    2.58
    是
    2.55
     Externe
    2.52
    欷
    2.50
     DONT
    2.47
     kommende
    2.44
     heilig
    2.44
    genodigd
    2.42
    Activations Density 0.008%

    No Known Activations