© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125438
    Prev
    Next
    INDEX
    Explanations

    decoration and alteration

    np_acts-logits-general · gemini-2.5-flash-lite

    awk commands and text alterations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    この
    0.49
    これ
    0.48
     நான
    0.47
     trimestre
    0.45
    ۴
    0.44
    ૪
    0.44
    RAL
    0.44
    ３
    0.43
    0.43
    される
    0.42
    POSITIVE LOGITS
     adjustments
    0.60
     adjustment
    0.55
     Adjusted
    0.53
     adjusts
    0.52
     alterations
    0.52
     ornaments
    0.52
     adjust
    0.50
     excuses
    0.50
     Adjustment
    0.49
     ставак
    0.49
    Activations Density 0.000%

    No Known Activations