© 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. 144415
    Prev
    Next
    INDEX
    Explanations

    noun or pronoun followed by punctuation

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

    create or calculate

    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
    formes
    0.48
    োগ্য
    0.48
    霰
    0.47
    LEXPORT
    0.46
     स्पून
    0.46
     Pued
    0.46
     \|\
    0.45
     亠
    0.45
     Radiological
    0.45
     rupam
    0.45
    POSITIVE LOGITS
    k
    0.50
    You
    0.48
     дли
    0.46
     stal
    0.43
    óz
    0.42
     roadblock
    0.41
    át
    0.41
    enso
    0.41
    Make
    0.41
    Berkeley
    0.41
    Activations Density 0.000%

    No Known Activations