© 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. 54185
    Prev
    Next
    INDEX
    Explanations

    explore new things

    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
    '
    -2.86
    </b>
    -2.58
    </
    -2.50
    鉭
    -2.48
     será
    -2.33
     aumenta
    -2.20
    </h1>
    -2.19
    
    -2.17
     necesitan
    -2.16
    鈰
    -2.16
    POSITIVE LOGITS
    𞤢
    2.78
    鳧
    2.73
    鏵
    2.72
    鈇
    2.70
    ेमाल
    2.69
     for
    2.66
    ꠥ
    2.42
    衎
    2.41
    尛
    2.41
    𞤥
    2.31
    Activations Density 0.016%

    No Known Activations