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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111623
    Prev
    Next
    INDEX
    Explanations

    digits and symbols

    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
    ’
    -2.70
    -
    -2.69
     Your
    -2.45
     be
    -2.44
     mocking
    -2.42
    があります
    -2.42
            
    -2.42
    ༀ
    -2.33
     $
    -2.28
     Find
    -2.20
    POSITIVE LOGITS
    蓐
    2.50
     櫃
    2.48
    歃
    2.45
    ✋
    2.34
    ]?
    2.33
    ⬇
    2.31
    牁
    2.30
     perplexing
    2.25
    ⁉
    2.23
     店内
    2.22
    Activations Density 0.310%

    No Known Activations