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. 494
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    i
    -2.22
     '
    -1.95
     '(
    -1.77
    Q
    -1.72
    『
    -1.71
    我們的
    -1.66
     identité
    -1.61
    甡
    -1.59
    الش
    -1.58
     sako
    -1.57
    POSITIVE LOGITS
    .
    1.77
    怱
    1.73
    fillment
    1.72
     spezielle
    1.72
     höhere
    1.66
    вяза
    1.66
    ilización
    1.64
    illite
    1.63
    médiaire
    1.62
     basteln
    1.60
    Activations Density 0.015%

    No Known Activations