© 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. 149845
    Prev
    Next
    INDEX
    Explanations

    change parts Firefox

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

    creative, lovely, kind, sweet, engineer

    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
     spéciale
    0.50
    LI
    0.48
    RI
    0.47
    Hon
    0.47
     Được
    0.47
    签订
    0.47
    য়
    0.46
    仙
    0.46
    Bi
    0.45
     নিকটে
    0.45
    POSITIVE LOGITS
     economía
    0.45
     भारतात
    0.45
    ыска
    0.44
    DOMstrings
    0.44
     quadrado
    0.42
     বাংলায়
    0.42
     کاربر
    0.42
     streetlight
    0.41
    Parameterized
    0.41
    ⚐
    0.41
    Activations Density 0.001%

    No Known Activations