© 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. 11489
    Prev
    Next
    INDEX
    Explanations

    highway numbers

    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
     luat
    -1.56
    짙
    -1.52
    ziasztok
    -1.52
    filé
    -1.48
    Они
    -1.38
    第七
    -1.38
    ޚ
    -1.38
     możemy
    -1.34
     colocación
    -1.33
     lämp
    -1.32
    POSITIVE LOGITS
     to
    2.33
    al
    1.68
    s
    1.53
    m
    1.49
    te
    1.48
    om
    1.47
     be
    1.40
    eb
    1.40
    em
    1.40
    on
    1.40
    Activations Density 0.032%

    No Known Activations