© 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. 16214
    Prev
    Next
    INDEX
    Explanations

    dump

    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
     erhö
    -2.63
    
    -2.59
     Ausblick
    -2.53
    鉛筆
    -2.48
     Again
    -2.48
     Hinsicht
    -2.47
    辚
    -2.41
     möglichen
    -2.36
     Could
    -2.36
     benö
    -2.34
    POSITIVE LOGITS
    ed
    3.14
    ⬮
    2.86
    埽
    2.81
    鱨
    2.80
    b
    2.78
    橚
    2.72
    澌
    2.67
    y
    2.63
    唧
    2.53
     RequestMethod
    2.50
    Activations Density 0.046%

    No Known Activations