© 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. 17626
    Prev
    Next
    INDEX
    Explanations

    questions about length or amount

    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
    ে
    0.67
    ي
    0.62
    苼
    0.57
    нда
    0.56
    影響
    0.56
    مل
    0.55
    شك
    0.54
    აპ
    0.54
    Об
    0.54
    มี
    0.52
    POSITIVE LOGITS
    f
    0.74
    v
    0.59
    b
    0.57
    d
    0.56
     of
    0.54
    t
    0.54
    m
    0.54
     len
    0.52
     '
    0.51
     S
    0.50
    Activations Density 0.000%

    No Known Activations