© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37205
    Prev
    Next
    INDEX
    Explanations

    Statistics, probability, data analysis

    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
    ፣
    0.37
     spite
    0.36
    jamin
    0.35
     وليس
    0.34
     egreg
    0.34
     sincer
    0.33
     mischiev
    0.33
     بدور
    0.33
     eternally
    0.33
     attent
    0.32
    POSITIVE LOGITS
     Конгрегация
    0.41
    unzione
    0.37
    저는
    0.37
    စိတ်အပိုင်း
    0.37
    ol
    0.37
    ɻ
    0.36
     crianças
    0.35
     नहीं
    0.35
    і
    0.35
    না
    0.35
    Activations Density 0.001%

    No Known Activations