© 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. 63582
    Prev
    Next
    INDEX
    Explanations

    preposition or noun followed by noun or verb

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

    Scanner in code

    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
    Negative Logits
    t
    0.56
    R
    0.55
    Pir
    0.50
    COVID
    0.47
    IV
    0.47
    rd
    0.45
    Pclass
    0.45
    C
    0.45
    )$$
    0.45
    YB
    0.45
    POSITIVE LOGITS
     قالب
    0.48
     jp
    0.45
     заявления
    0.44
    otipos
    0.44
     പുറ
    0.43
     canalicul
    0.43
     उसने
    0.42
    ulado
    0.42
     notificación
    0.42
     azules
    0.42
    Activations Density 0.001%

    No Known Activations