© 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. 260933
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     టి
    0.49
     నాలుగు
    0.47
     कालीन
    0.47
     場
    0.47
     ග
    0.47
     bốn
    0.47
     ثانيه
    0.47
     ଗ
    0.47
     发
    0.45
     డి
    0.45
    POSITIVE LOGITS
    O
    0.49
    রাশ
    0.48
    EW
    0.47
    AST
    0.47
    KJ
    0.47
    SE
    0.46
    ESD
    0.46
    フィルタ
    0.45
    opy
    0.45
    МА
    0.45
    Activations Density 0.001%

    No Known Activations