© 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. 40-GEMMASCOPE-2-RES-262K
    7. 24664
    Prev
    Next
    INDEX
    Explanations

    as a separator

    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
    Negative Logits
    and
    0.50
    ous
    0.46
    ing
    0.45
     into
    0.44
    about
    0.44
     and
    0.43
    e
    0.43
     about
    0.43
    at
    0.42
    related
    0.41
    POSITIVE LOGITS
     કાર્યવાહી
    0.43
    VideoButton
    0.41
    스는
    0.41
    RangeException
    0.40
     فائلوں
    0.40
    keypress
    0.38
     pály
    0.38
    
    0.38
    𒊬
    0.38
    юз
    0.38
    Activations Density 0.038%

    No Known Activations