© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189564
    Prev
    Next
    INDEX
    Explanations

    appearance or modification

    np_acts-logits-general · gemini-2.5-flash-lite

    planet called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ῥ
    0.57
    xhr
    0.56
    ர
    0.55
    lis
    0.53
    ри
    0.52
    ඃ
    0.52
    ក្រុមហ៊ុន
    0.50
    فير
    0.50
    નિક
    0.50
    いただきます
    0.50
    POSITIVE LOGITS
     IF
    0.49
     dose
    0.47
     shout
    0.47
     luck
    0.47
     "
    0.46
     definitions
    0.45
     ident
    0.45
     elucidation
    0.44
     appearance
    0.43
     grund
    0.43
    Activations Density 0.000%

    No Known Activations