© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132972
    Prev
    Next
    INDEX
    Explanations

    intensifiers for problematic qualifiers

    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
     sniper
    0.44
     sketchbook
    0.42
     asimismo
    0.41
     softener
    0.39
    誂
    0.39
    嗌
    0.38
     color
    0.38
     skipper
    0.38
    ursery
    0.37
     sweater
    0.37
    POSITIVE LOGITS
     (>
    0.46
     jõ
    0.38
     reparations
    0.38
     unclean
    0.37
     Ellen
    0.35
    Ellen
    0.35
     Horm
    0.35
     Holog
    0.34
     reparation
    0.34
     Wee
    0.34
    Activations Density 0.001%

    No Known Activations