© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3815
    Prev
    Next
    INDEX
    Explanations

    yaml.dump

    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
     abdom
    0.78
    )
    0.73
    ים
    0.70
     isang
    0.60
     cranial
    0.58
     permukaan
    0.58
     частей
    0.57
     چک
    0.57
     evenly
    0.57
     elast
    0.57
    POSITIVE LOGITS
    老
    0.71
    tech
    0.58
    天
    0.56
    TextUtils
    0.55
    ूव
    0.54
    ent
    0.54
    rh
    0.54
    ate
    0.54
    社
    0.54
    ufl
    0.53
    Activations Density 0.001%

    No Known Activations