© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105129
    Prev
    Next
    INDEX
    Explanations

    Koh, Kohana, Kohden, KOH examination, 解决办法

    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_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
    ";
    
    -3.22
     That
    -3.22
     This
    -2.98
    </h3>
    -2.88
    殲
    -2.70
    </i>
    -2.66
    皺
    -2.63
     możliwe
    -2.44
    ществ
    -2.39
    
    -2.33
    POSITIVE LOGITS
    am
    2.97
    p
    2.84
     atau
    2.70
    埽
    2.48
     pessoais
    2.48
    v
    2.48
     that
    2.34
    </h2>
    2.33
     یا
    2.33
    ’
    2.30
    Activations Density 0.001%

    No Known Activations