© 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. 22-GEMMASCOPE-RES-131K
    7. 130403
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    になったら
    -1.70
     and
    -1.65
    gettyimages
    -1.52
    際には
    -1.44
    ઃ
    -1.43
    ありますか
    -1.43
    際は
    -1.43
    抨
    -1.40
    づけ
    -1.38
    :
    -1.38
    POSITIVE LOGITS
    upuncture
    1.38
    vák
    1.37
    や
    1.34
     consé
    1.29
    缡
    1.28
    がありますが
    1.28
    łk
    1.27
     nossos
    1.27
    に
    1.26
    ១
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.