© 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. 147564
    Prev
    Next
    INDEX
    Explanations

    oil and gas value chain

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

    pounds unit of weight

    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
     війни
    0.58
     Atención
    0.57
     financiación
    0.54
     ໜ
    0.53
    inizio
    0.53
     comportamenti
    0.53
     પાણી
    0.53
     народного
    0.53
    ха
    0.51
    ività
    0.50
    POSITIVE LOGITS
     assessors
    0.54
     identifiers
    0.51
     pastures
    0.50
     experts
    0.50
     checkpoints
    0.49
     elders
    0.49
     e
    0.48
     acres
    0.48
     o
    0.46
     jour
    0.46
    Activations Density 0.000%

    No Known Activations