© 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. 146535
    Prev
    Next
    INDEX
    Explanations

    events and specific quantities

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

    adjective suffixes or specific things

    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
     જવાબ
    0.48
    lanan
    0.46
     आकर
    0.45
    civil
    0.44
     nhắn
    0.44
    alem
    0.43
    endem
    0.43
    缱
    0.43
     данни
    0.42
    ins
    0.42
    POSITIVE LOGITS
     SCHOOL
    0.53
     HOURS
    0.52
     Pediatric
    0.48
     \|
    0.47
     HOUR
    0.47
     hours
    0.47
     lifespan
    0.46
     fantasy
    0.46
     bluetooth
    0.46
     〜
    0.45
    Activations Density 0.003%

    No Known Activations