© 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. 34429
    Prev
    Next
    INDEX
    Explanations

    sports ball context

    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
     этих
    -1.47
     of
    -1.43
     \
    -1.41
    ’
    -1.34
    様な
    -1.30
    
    -1.27
    这些
    -1.27
    else
    -1.24
     lavable
    -1.23
    by
    -1.23
    POSITIVE LOGITS
    pAd
    1.32
     transforms
    1.27
    PLIANCE
    1.27
     請
    1.26
    <bos>
    1.26
     brevemente
    1.23
    ☆☆
    1.23
     Democrá
    1.22
    翃
    1.21
     Hva
    1.20
    Activations Density 0.007%

    No Known Activations