© 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. 34-GEMMASCOPE-RES-131K
    7. 118935
    Prev
    Next
    INDEX
    Explanations

    idea behind, logic behind, stories behind, among

    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
    Between
    -1.95
    between
    -1.76
    Within
    -1.70
    Around
    -1.65
    Across
    -1.63
     Within
    -1.62
    Through
    -1.59
     Between
    -1.59
    Against
    -1.58
     Against
    -1.52
    POSITIVE LOGITS
    thog
    0.91
    槙
    0.85
    sterious
    0.85
    腚
    0.83
    création
    0.82
     metales
    0.81
     molto
    0.80
    vascular
    0.80
     terciopelo
    0.79
    嗲
    0.79
    Activations Density 0.138%

    No Known Activations