© 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. 90678
    Prev
    Next
    INDEX
    Explanations

    field or cost related phrases

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

    ad extensions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    潴
    0.47
     idealized
    0.46
    调节
    0.46
     прият
    0.46
    瓠
    0.44
    挚
    0.43
     እንዲ
    0.42
     აღ
    0.42
    ГИ
    0.42
     газа
    0.42
    POSITIVE LOGITS
     partecipanti
    0.44
    ransfer
    0.43
    出て
    0.42
    獲得
    0.42
    ceans
    0.41
    是用
    0.41
    紙
    0.41
     adds
    0.40
    obytes
    0.40
     emissions
    0.40
    Activations Density 0.000%

    No Known Activations