© 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. 50937
    Prev
    Next
    INDEX
    Explanations

    packaging, supplier, came later

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

    visit, complaint, obstacles, redundant, motion study, heritage night

    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
     capitalise
    0.52
     capitalize
    0.46
    周
    0.44
     -
    0.43
     tai
    0.42
     imagina
    0.42
     calculate
    0.42
     oui
    0.42
    に必要な
    0.41
     Í
    0.41
    POSITIVE LOGITS
     које
    0.49
    衅
    0.47
    فه
    0.46
    تون
    0.46
     крово
    0.43
    ستم
    0.42
     ഷ
    0.42
    یم
    0.42
    тво
    0.42
    چه
    0.41
    Activations Density 0.000%

    No Known Activations