© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27281
    Prev
    Next
    INDEX
    Explanations

    committing database changes

    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_40_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
     посо
    0.43
     khoan
    0.39
     குறி
    0.39
     repur
    0.39
     McEl
    0.39
    毆
    0.37
     mahogany
    0.37
     ២
    0.37
     мра
    0.36
     restriction
    0.36
    POSITIVE LOGITS
     commit
    1.75
    commit
    1.71
     committing
    1.70
     Commit
    1.66
    Commit
    1.63
     commits
    1.59
     committed
    1.50
     COMMIT
    1.50
    committed
    1.41
     Committed
    1.33
    Activations Density 0.016%

    No Known Activations