© 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. 657
    Prev
    Next
    INDEX
    Explanations

    React class definition

    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
     those
    -1.73
     then
    -1.63
     them
    -1.49
     Mereka
    -1.44
     тях
    -1.42
    tisgarh
    -1.38
     вони
    -1.32
    氿
    -1.31
     you
    -1.30
     obligación
    -1.30
    POSITIVE LOGITS
     appartements
    1.27
    ⓝ
    1.27
     Fiscalía
    1.25
    嗵
    1.21
    inigung
    1.18
     diferentes
    1.17
     luat
    1.17
    ’”
    1.16
     tenté
    1.16
    ひとつ
    1.16
    Activations Density 0.089%

    No Known Activations