© 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. 127434
    Prev
    Next
    INDEX
    Explanations

    adequate expertise

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

    implies what should be

    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
    LowerCase
    0.58
     রাশিয়া
    0.41
     rá
    0.41
     _;
    0.41
     bądź
    0.41
     disappoint
    0.40
     estím
    0.40
     RNA
    0.40
     dissociate
    0.39
     _,
    0.39
    POSITIVE LOGITS
    ದ್ಧ
    0.46
    inois
    0.46
    ខ
    0.43
    onym
    0.43
     Noeud
    0.42
     jaar
    0.42
    स्रोत
    0.41
    ಿಕ್
    0.41
    ahanglan
    0.41
    кну
    0.40
    Activations Density 0.001%

    No Known Activations