© 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. 3113
    Prev
    Next
    INDEX
    Explanations

    personalized marketing, content, experiences

    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
    t
    0.98
    laan
    0.85
    ların
    0.82
    lar
    0.81
    s
    0.80
    mmmm
    0.74
    ian
    0.73
    a
    0.73
    ing
    0.73
    nya
    0.72
    POSITIVE LOGITS
    ни
    1.10
    те
    1.05
    ли
    1.01
    ى
    0.98
    то
    0.97
    ной
    0.84
    지
    0.83
    ز
    0.82
    هاي
    0.81
    ها
    0.80
    Activations Density 0.006%

    No Known Activations