© 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. 191219
    Prev
    Next
    INDEX
    Explanations

    legal, official, or financial documents

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

    technical identifiers and methods

    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
     countryside
    0.55
    ὢ
    0.53
     रक्कम
    0.52
     গ্রামা
    0.48
    ᓴ
    0.48
     इनका
    0.46
    ૄ
    0.46
     dificuldade
    0.46
     skillset
    0.46
    ᓱ
    0.46
    POSITIVE LOGITS
    engan
    0.46
    oy
    0.46
    يج
    0.44
    aturally
    0.44
    wal
    0.43
    le
    0.43
    percaya
    0.42
     Attorneys
    0.42
    ust
    0.42
    arg
    0.41
    Activations Density 0.000%

    No Known Activations