© 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. 153141
    Prev
    Next
    INDEX
    Explanations

    non-English or multilingual content

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

    He pretends to describe situations

    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
    Ket
    0.52
    ments
    0.50
    V
    0.50
    A
    0.50
    or
    0.50
    ment
    0.49
    com
    0.47
    H
    0.47
    th
    0.46
    work
    0.46
    POSITIVE LOGITS
    ені
    0.51
    笊
    0.48
     የተለያዩ
    0.46
    しまい
    0.45
     аутох
    0.44
     πιο
    0.44
     разных
    0.44
    結構
    0.44
     различни
    0.44
    υτό
    0.44
    Activations Density 0.000%

    No Known Activations