© 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. 672
    Prev
    Next
    INDEX
    Explanations

    top part or surface

    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
    (
    -3.52
    '
    -3.50
    *
    -3.16
    ↵↵
    -2.89
    <
    -2.78
    ?
    -2.66
     —
    -2.64
    ;
    -2.47
          
    -2.39
    \
    -2.39
    POSITIVE LOGITS
    ୌ
    2.78
    𐐪
    2.75
     boast
    2.59
     efekty
    2.58
    ጁ
    2.56
    Fär
    2.50
    ically
    2.42
     москва
    2.41
     painstaking
    2.41
     projekty
    2.39
    Activations Density 0.020%

    No Known Activations