© 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. 6911
    Prev
    Next
    INDEX
    Explanations

    subset of

    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
    1
    0.99
    した
    0.92
     you
    0.89
    他
    0.86
    ่
    0.82
    נה
    0.82
    ido
    0.81
    یت
    0.78
    ayette
    0.77
    Í
    0.77
    POSITIVE LOGITS
    i
    1.25
    ي
    1.25
    ت
    1.06
    ри
    1.01
    ו
    1.01
    ٣
    0.91
    m
    0.90
    م
    0.90
    ে
    0.90
    т
    0.89
    Activations Density 0.023%

    No Known Activations