© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 764
    Prev
    Next
    INDEX
    Explanations

    names followed by verbs

    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
     has
    -1.97
     or
    -1.97
     while
    -1.95
     itself
    -1.92
     with
    -1.76
     is
    -1.70
     just
    -1.63
     all
    -1.59
     what
    -1.57
     six
    -1.52
    POSITIVE LOGITS
     are
    2.47
    ⑊
    1.63
     trám
    1.61
    weren
    1.59
     ส์
    1.55
    considered
    1.54
    increased
    1.53
     แต่
    1.53
    possibly
    1.52
    voiture
    1.52
    Activations Density 0.036%

    No Known Activations