© 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. 129832
    Prev
    Next
    INDEX
    Explanations

    compromise, death, table, released, Levi

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

    imposing external Fundamental

    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
    イッチ
    0.47
    ンド
    0.45
    HYDRO
    0.45
    UTO
    0.44
    ഥ
    0.44
    ッター
    0.44
    トー
    0.44
    れば
    0.44
     給
    0.43
    サンプル
    0.43
    POSITIVE LOGITS
     compromising
    0.50
     compromise
    0.46
     fluctuations
    0.44
     Caedwalla
    0.42
     fluctuation
    0.42
     sportif
    0.42
     decay
    0.41
     Με
    0.41
    Mex
    0.41
     Cie
    0.41
    Activations Density 0.001%

    No Known Activations