© 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. 131316
    Prev
    Next
    INDEX
    Explanations

    categorical features and Chi-Square Test

    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
     जिम्मेदार
    0.44
     wanneer
    0.43
     когато
    0.43
     Technique
    0.40
     Técnica
    0.38
     প্রয়োজন
    0.38
     отсутствие
    0.37
    槻
    0.37
     Toch
    0.37
     полез
    0.37
    POSITIVE LOGITS
    ังสือ
    0.42
    递
    0.42
     actual
    0.41
     sond
    0.41
    完
    0.41
    Bs
    0.38
    fillna
    0.38
     steeper
    0.38
     steep
    0.37
    멤
    0.37
    Activations Density 0.000%

    No Known Activations