© 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. 10-GEMMASCOPE-RES-131K
    7. 42090
    Prev
    Next
    INDEX
    Explanations

    math formulas, infections, names, phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    whitespace or indentation formatting in technical documents and code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    k
    -2.13
    n
    -2.11
    p
    -2.09
    s
    -2.03
    m
    -1.95
     brancas
    -1.93
    Before
    -1.93
    絕對
    -1.91
     excessively
    -1.89
     peruano
    -1.89
    POSITIVE LOGITS
    </i>
    2.77
    蛲
    2.61
    蛱
    2.56
    ⩕
    2.27
    
    2.20
    觏
    2.11
    奁
    2.05
    ⟣
    2.05
    ⩴
    2.03
    鸸
    2.00
    Activations Density 0.000%

    No Known Activations