© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 109056
    Prev
    Next
    INDEX
    Explanations

    units and context clues

    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
    ۵
    0.81
    ۴
    0.75
    9
    0.73
    사
    0.73
    나
    0.73
    Пе
    0.73
    ۶
    0.73
     auspicious
    0.72
    두
    0.72
     ambassador
    0.71
    POSITIVE LOGITS
    ن
    0.73
    er
    0.71
    ar
    0.71
     That
    0.70
    śmy
    0.70
    ir
    0.66
    ing
    0.65
    䡈
    0.65
    z
    0.64
    czą
    0.64
    Activations Density 0.000%

    No Known Activations