© 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. 176520
    Prev
    Next
    INDEX
    Explanations

    three young, join dunkin, stewart gardner

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

    measurement and signals

    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
    agro
    0.49
    पेड
    0.45
    реже
    0.45
    peda
    0.45
    bras
    0.44
    steacher
    0.43
    አ
    0.43
    پاک
    0.42
    Для
    0.42
    atherm
    0.42
    POSITIVE LOGITS
     stdin
    0.43
     delineation
    0.43
    łę
    0.42
     pathlib
    0.41
     LPTMR
    0.40
    藏
    0.40
     neoplastic
    0.40
     aspiration
    0.40
     மாதிர
    0.40
    眞
    0.40
    Activations Density 0.000%

    No Known Activations