© 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. 76024
    Prev
    Next
    INDEX
    Explanations

    symbolic identifiers and names

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

    map words to ids

    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
    香港
    0.48
    Ｉ
    0.44
    ዠ
    0.43
    किस्तानी
    0.43
    ᴵ
    0.42
    William
    0.41
    谢
    0.41
    ቮ
    0.40
    若
    0.40
    ঐ
    0.40
    POSITIVE LOGITS
     polymerase
    0.46
    هم
    0.45
     Virology
    0.45
    訓練
    0.44
    ხ
    0.44
     Genomic
    0.43
     barrios
    0.42
     digitalization
    0.42
     बायो
    0.42
     cholinergic
    0.41
    Activations Density 0.000%

    No Known Activations