© 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. 10-GEMMASCOPE-RES-131K
    7. 84110
    Prev
    Next
    INDEX
    Explanations

    actions and procedures

    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
     
    -2.83
    </strong>
    -2.48
     Your
    -2.42
    2
    -2.23
     Referring
    -2.19
     Extensive
    -2.19
    焿
    -2.14
    Ideally
    -2.13
    蛲
    -2.09
    
    -2.08
    POSITIVE LOGITS
     processes
    2.98
    诹
    2.89
    袪
    2.50
    塲
    2.47
    ="")
    2.47
    vantaged
    2.47
    自身的
    2.45
    聿
    2.45
    晅
    2.42
    䊐
    2.42
    Activations Density 0.015%

    No Known Activations