© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129035
    Prev
    Next
    INDEX
    Explanations

    `if __name__ == "__main__"`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     reactants
    0.46
     reactant
    0.44
     avatar
    0.43
    ាំង
    0.43
     pokaz
    0.42
     films
    0.41
     avatars
    0.39
    喺
    0.39
     radius
    0.39
     firms
    0.39
    POSITIVE LOGITS
    BufferedWriter
    0.50
    uyết
    0.47
    Piano
    0.46
    ılara
    0.46
    slee
    0.45
    ět
    0.43
    Trimethyl
    0.43
    瀝
    0.43
    ão
    0.43
    äten
    0.43
    Activations Density 0.002%

    No Known Activations