© 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. 65727
    Prev
    Next
    INDEX
    Explanations

    logos, foreign punctuation

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

    providing or enabling actions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     INPUT
    0.46
     २
    0.46
    論文
    0.46
     кисло
    0.45
     ಮಾಹಿತ
    0.43
    banam
    0.43
     гимна
    0.43
    hyperref
    0.42
     NONCLUSTERED
    0.42
     కల
    0.42
    POSITIVE LOGITS
     coûte
    0.51
    ز
    0.49
     allows
    0.48
    Provide
    0.48
     consente
    0.48
     pozwala
    0.46
     proporciona
    0.46
    Chris
    0.46
    ಯ
    0.46
    ع
    0.45
    Activations Density 0.001%

    No Known Activations