Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 20364
    Prev
    Next
    INDEX
    Explanations

    publishing values

    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
    ↵
    1.15
    ו
    0.97
    ę
    0.95
    า
    0.90
    ą
    0.89
     I
    0.85
    ா
    0.82
    ب
    0.82
    де
    0.80
    ल
    0.78
    POSITIVE LOGITS
     of
    1.20
    and
    1.16
     in
    1.02
     for
    0.91
    of
    0.85
    ma
    0.81
    for
    0.79
    book
    0.77
     and
    0.75
    daki
    0.75
    Activations Density 0.164%

    No Known Activations