© 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. 210409
    Prev
    Next
    INDEX
    Explanations

    moving on

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

    general framework or outline

    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
    MANY
    0.55
    MEDICAL
    0.55
    शांत
    0.52
    ДА
    0.52
    당
    0.52
    ISM
    0.50
    RAEL
    0.50
    платы
    0.49
    פק
    0.48
    ᕗ
    0.48
    POSITIVE LOGITS
    一定的
    0.43
    ucch
    0.42
     Americans
    0.42
     pottery
    0.42
     diminutive
    0.41
    k
    0.41
     Andy
    0.40
     එක
    0.39
     flock
    0.39
    redis
    0.39
    Activations Density 0.000%

    No Known Activations