Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 3403
    Prev
    Next
    INDEX
    Explanations

    domain names

    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_16_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
    。
    0.47
    ncnc
    0.45
    tól
    0.43
    striatis
    0.41
     sorprendente
    0.40
    Ꮸ
    0.39
     namani
    0.38
     Մ
    0.38
    ErrorClazz
    0.38
    。《
    0.38
    POSITIVE LOGITS
     and
    0.73
     in
    0.69
    ق
    0.57
    도
    0.56
     are
    0.53
    ید
    0.52
     or
    0.51
     the
    0.48
    신
    0.47
    ö
    0.46
    Activations Density 0.672%

    No Known Activations