© 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. 113905
    Prev
    Next
    INDEX
    Explanations

    there is or are

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

    asking questions, gaining information

    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
     皮
    0.49
     across
    0.48
     मेट
    0.46
    鴨
    0.44
    MAT
    0.43
    Across
    0.43
     ブーツ
    0.43
    PAD
    0.43
    ।-
    0.43
     eradic
    0.42
    POSITIVE LOGITS
     hí
    0.57
     fréquemment
    0.49
     inspiración
    0.47
     krank
    0.47
     bü
    0.47
    şe
    0.47
     úpl
    0.47
    şu
    0.46
     états
    0.46
     bibliothèque
    0.46
    Activations Density 0.001%

    No Known Activations