© 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. 123856
    Prev
    Next
    INDEX
    Explanations

    military commander and Reagan did

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

    bridge, indicating, suggesting, services, park, power

    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
     कैंपस
    0.47
    чого
    0.47
    Herd
    0.47
    ⤥
    0.47
    ondo
    0.46
     Township
    0.46
    ুলে
    0.46
    鄉
    0.45
     जिले
    0.45
     高校
    0.44
    POSITIVE LOGITS
    있다
    0.48
    }!
    0.44
     reprodu
    0.44
    ेडियम
    0.44
     cumulative
    0.43
     defocus
    0.42
    ாதாரண
    0.42
     defocused
    0.42
     trit
    0.41
     convexes
    0.41
    Activations Density 0.001%

    No Known Activations