© 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. 10597
    Prev
    Next
    INDEX
    Explanations

    secret, elasticity, guidance, reality

    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
     miraculously
    0.46
    P
    0.45
    ту
    0.45
    F
    0.44
    全
    0.44
    processed
    0.43
    ম
    0.43
    Tot
    0.42
    Ֆ
    0.42
    C
    0.42
    POSITIVE LOGITS
     международных
    0.52
     ڈھ
    0.51
     slats
    0.48
     adhesives
    0.47
    রাজনৈতিক
    0.47
     عائد
    0.44
     кеңселер
    0.44
     یورپی
    0.44
    哂
    0.44
    amientos
    0.44
    Activations Density 0.002%

    No Known Activations