© 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. 16-GEMMASCOPE-2-RES-262K
    4. 1446
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

    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
     demás
    0.75
    й
    0.73
    یم
    0.71
    ні
    0.66
    니
    0.63
    ی
    0.63
    ِ
    0.61
    ین
    0.61
    жи
    0.61
    of
    0.61
    POSITIVE LOGITS
     ETFs
    0.81
     October
    0.77
    ↵↵
    0.72
     Create
    0.68
     alebo
    0.68
     A
    0.67
     September
    0.67
     HPV
    0.67
    ’
    0.65
     Arizona
    0.64
    Activations Density 0.053%

    No Known Activations