© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 24113
    Prev
    Next
    INDEX
    Explanations

    hurt, hurting, hurtling

    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
     داله
    0.40
     envision
    0.38
     factorizar
    0.36
    "),],
    0.36
    CREATED
    0.36
     கொண்டனர்
    0.36
     yks
    0.35
     ঘি
    0.35
    灸
    0.35
     REGIUNI
    0.35
    POSITIVE LOGITS
     Спорт
    0.41
    Money
    0.41
    糟糕
    0.39
    USD
    0.39
     земле
    0.38
    ലെസ്
    0.38
     hurting
    0.38
    Kings
    0.38
    But
    0.37
     oneself
    0.37
    Activations Density 0.000%

    No Known Activations