© 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. 176912
    Prev
    Next
    INDEX
    Explanations

    information and transactional phrases

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

    research and exploration

    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
    AK
    0.50
    IN
    0.49
    م
    0.46
    VA
    0.45
    Arithmetic
    0.45
    ปาก
    0.45
    AR
    0.44
    ม
    0.43
    Hashing
    0.43
    Affine
    0.43
    POSITIVE LOGITS
     thankful
    0.47
     অবস্থায়
    0.46
    ပို့
    0.45
    phor
    0.45
     lẫn
    0.45
    抒
    0.45
     conserved
    0.45
     ಕ್
    0.45
    alaya
    0.45
     hài
    0.45
    Activations Density 0.000%

    No Known Activations