© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118868
    Prev
    Next
    INDEX
    Explanations

    forms of harmony

    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_34/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
    بانی
    -0.77
     rhetorical
    -0.74
     характера
    -0.73
     Reaktion
    -0.72
    Executors
    -0.71
     finan
    -0.71
    ា
    -0.71
     финан
    -0.71
     MainAxisSize
    -0.70
    ohyd
    -0.70
    POSITIVE LOGITS
    harmon
    1.68
     Harmon
    1.66
    harmony
    1.44
     harmon
    1.42
    Harmon
    1.40
    Harmony
    1.34
     Harmony
    1.33
     harmony
    1.28
     harmonize
    1.18
     harmonious
    1.15
    Activations Density 0.020%

    No Known Activations