© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28442
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    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_22/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
     eventually
    -1.10
     occasionally
    -1.04
    当初
    -0.97
     possible
    -0.96
     family
    -0.93
     then
    -0.91
    著名
    -0.91
     or
    -0.90
     stone
    -0.89
     How
    -0.87
    POSITIVE LOGITS
    nofollow
    1.09
    endpush
    1.08
     fuper
    1.02
     poffe
    1.02
    久し
    1.00
    ステム
    1.00
    蟎
    1.00
    あぁ
    0.99
    少しでも
    0.98
     cinqu
    0.98
    Activations Density 0.020%

    No Known Activations