© 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. 1245
    Prev
    Next
    INDEX
    Explanations

    relative imports and many associations

    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
    or
    -2.34
    A
    -2.16
    1
    -2.02
    ent
    -1.95
    ti
    -1.95
    if
    -1.91
    j
    -1.89
    and
    -1.88
    id
    -1.83
    out
    -1.80
    POSITIVE LOGITS
    ángulo
    1.84
    驺
    1.80
    拶
    1.77
    humble
    1.66
    灩
    1.66
    szt
    1.66
    businessman
    1.63
    yyb
    1.60
     excepto
    1.60
    OUTUBE
    1.59
    Activations Density 0.001%

    No Known Activations