© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46458
    Prev
    Next
    INDEX
    Explanations

    indicates functionality

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

    do. The program execution

    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
    桻
    0.47
     マル
    0.45
    ონის
    0.44
    splitLength
    0.44
    дцать
    0.44
     подготовлено
    0.44
     определения
    0.43
    номер
    0.43
    探し
    0.43
     подачи
    0.42
    POSITIVE LOGITS
    喎
    0.46
    iii
    0.45
    ikon
    0.43
     Promenade
    0.42
    ido
    0.41
     deh
    0.40
    ؑ
    0.40
    orithm
    0.40
    ii
    0.40
     Anglia
    0.40
    Activations Density 0.000%

    No Known Activations