© 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. 118959
    Prev
    Next
    INDEX
    Explanations

    actions, requirements, or capabilities

    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
    没能
    -1.70
     alimentare
    -1.66
     饼
    -1.65
    "=
    -1.65
    decine
    -1.63
    윔
    -1.62
     successes
    -1.59
    です
    -1.59
     бъдат
    -1.59
    kových
    -1.56
    POSITIVE LOGITS
    -
    2.59
     Three
    1.96
     There
    1.93
    es
    1.83
     like
    1.80
     all
    1.79
     Does
    1.77
     Eight
    1.73
    It
    1.70
     alot
    1.70
    Activations Density 0.021%

    No Known Activations