© 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. 87121
    Prev
    Next
    INDEX
    Explanations

    foreign words and punctuation

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

    descriptive adjectives and nouns

    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
    banners
    0.54
    batter
    0.52
     wallpapers
    0.52
    in
    0.51
    innov
    0.50
    quite
    0.48
    Batter
    0.48
    rapers
    0.46
    ଁ
    0.46
    𝚊
    0.46
    POSITIVE LOGITS
    ۔
    0.56
     zamknię
    0.54
    };
    0.48
     دائو
    0.48
     człowieka
    0.47
    。
    0.47
    的一个
    0.46
     vértice
    0.46
     Otros
    0.45
    嚢
    0.45
    Activations Density 0.000%

    No Known Activations