© 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. 25444
    Prev
    Next
    INDEX
    Explanations

    customization and requests

    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
    ציה
    -1.07
    jskiej
    -1.03
     correta
    -1.03
     inalámb
    -1.01
     查看
    -0.99
    髂
    -0.99
    correctly
    -0.98
    enziale
    -0.98
     inalámbrica
    -0.97
    properly
    -0.97
    POSITIVE LOGITS
     cualquier
    1.73
     any
    1.71
     customized
    1.59
     custom
    1.57
     customization
    1.54
     customize
    1.47
     también
    1.42
     for
    1.39
     также
    1.35
     request
    1.34
    Activations Density 0.033%

    No Known Activations