© 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. 71307
    Prev
    Next
    INDEX
    Explanations

    recommended Science, conducted during, dislike strategy, always said

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

    mass unit kg kilograms

    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
    6
    0.52
    鱼
    0.49
    柠檬
    0.48
    7
    0.47
    5
    0.47
    智
    0.46
    肾
    0.46
    CG
    0.46
     γνωσ
    0.45
    护理
    0.45
    POSITIVE LOGITS
     infrastrukt
    0.48
     политика
    0.45
     extremism
    0.44
    frast
    0.43
    infrastructure
    0.43
     expropri
    0.42
     infrast
    0.42
     inmue
    0.41
     Deccan
    0.41
     politica
    0.41
    Activations Density 0.000%

    No Known Activations