© 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. 118940
    Prev
    Next
    INDEX
    Explanations

    historical facts and explanations

    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
     scrive
    -1.02
    ֲ
    -0.94
    וֹ
    -0.90
    וּ
    -0.89
    lenül
    -0.88
    の影響
    -0.86
    sibilities
    -0.82
    ₁(
    -0.81
    kinci
    -0.80
    囂
    -0.80
    POSITIVE LOGITS
     knowled
    1.69
     knowledge
    1.66
     narration
    1.53
     explanations
    1.49
     explain
    1.48
     informative
    1.48
     commentary
    1.42
     narr
    1.39
     knowledgeable
    1.39
     history
    1.36
    Activations Density 0.009%

    No Known Activations