© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25939
    Prev
    Next
    INDEX
    Explanations

    writer

    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
    ’
    -2.63
    ing
    -2.52
    2
    -2.45
    O
    -2.36
    u
    -2.33
    ”
    -2.31
    M
    -2.31
    e
    -2.28
    1
    -2.22
    R
    -2.19
    POSITIVE LOGITS
    狆
    2.44
    </i>
    2.39
     发型
    2.38
    
    2.38
    ית
    2.27
    eté
    2.11
    ⦊
    2.11
    
    2.03
    
    2.03
    我們
    2.03
    Activations Density 0.007%

    No Known Activations