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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9651
    Prev
    Next
    INDEX
    Explanations

    abbreviations in technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ہ
    0.72
     you
    0.70
    ้
    0.69
     a
    0.69
    0
    0.68
    на
    0.67
    im
    0.65
     et
    0.65
    ression
    0.65
    ad
    0.63
    POSITIVE LOGITS
     воздей
    0.73
     rozwiąz
    0.73
     подклю
    0.71
     образом
    0.69
     нажа
    0.68
     издели
    0.66
     оружи
    0.65
     bienvenidas
    0.64
     поня
    0.64
     подозре
    0.63
    Activations Density 0.186%

    No Known Activations