© 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. 2355
    Prev
    Next
    INDEX
    Explanations

    defining clauses using which

    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
    Negative Logits
    '
    0.46
     مختلفة
    0.40
     Montgomery
    0.39
     Jupyter
    0.39
    ०
    0.39
     что
    0.38
     Walking
    0.38
     เช่น
    0.38
     Rendering
    0.37
     这个
    0.37
    POSITIVE LOGITS
     является
    0.47
     কিনা
    0.46
     wiederum
    0.46
     characterised
    0.44
     tambien
    0.42
     also
    0.42
    は
    0.41
     भी
    0.40
     incidentally
    0.39
     också
    0.39
    Activations Density 0.080%

    No Known Activations