Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 464
    Prev
    Next
    INDEX
    Explanations

    actions and descriptions of staff

    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
     as
    -1.97
     of
    -1.97
     for
    -1.59
     Would
    -1.59
     in
    -1.59
     an
    -1.58
     that
    -1.52
     Besides
    -1.49
     not
    -1.47
     After
    -1.42
    POSITIVE LOGITS
    をしました
    1.69
    Etimología
    1.68
    whelming
    1.66
    狆
    1.58
    CURSO
    1.56
     wszystkie
    1.55
     tiveram
    1.54
     alimentare
    1.52
    をしています
    1.52
     какие
    1.47
    Activations Density 0.005%

    No Known Activations