© 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. 564
    Prev
    Next
    INDEX
    Explanations

    latex alignment commands

    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
     is
    0.76
    dan
    0.60
     are
    0.59
    ،
    0.54
    \
    0.53
     was
    0.52
    ၊
    0.52
    幡
    0.51
     at
    0.50
     tại
    0.50
    POSITIVE LOGITS
    in
    0.86
    ת
    0.86
    ر
    0.85
    il
    0.84
    و
    0.81
    ه
    0.81
    р
    0.77
    ร
    0.77
    ו
    0.77
    ר
    0.73
    Activations Density 0.001%

    No Known Activations