© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109722
    Prev
    Next
    INDEX
    Explanations

    correction invalidates other actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    underscore
    0.41
    לית
    0.40
    구
    0.38
    тя
    0.37
    רי
    0.37
    ק
    0.37
    が
    0.36
    а
    0.36
    ור
    0.35
    ד
    0.35
    POSITIVE LOGITS
     ().
    0.48
     seulement
    0.45
     negligent
    0.45
     namelijk
    0.45
    rawberry
    0.44
     নিষেধ
    0.43
     unpredictable
    0.42
     Didn
    0.42
     établ
    0.42
     strawberries
    0.42
    Activations Density 0.018%

    No Known Activations