© 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. 118957
    Prev
    Next
    INDEX
    Explanations

    library names and versions

    np_acts-logits-general · gemini-2.5-flash-lite

    code-related tokens such as library names, package identifiers, version numbers, and configuration paths in programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     that
    -2.05
     their
    -1.99
     on
    -1.92
     would
    -1.73
     might
    -1.59
     may
    -1.53
     your
    -1.50
     where
    -1.49
     during
    -1.45
     will
    -1.44
    POSITIVE LOGITS
     robuste
    1.53
    gni
    1.50
    </i>
    1.48
    ,",
    1.47
     EXAMPLES
    1.45
     bénéficient
    1.44
     drei
    1.43
    if
    1.41
     savait
    1.41
    tych
    1.39
    Activations Density 0.449%

    No Known Activations