© 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. 31-GEMMASCOPE-2-RES-262K
    7. 44444
    Prev
    Next
    INDEX
    Explanations

    `noverlap` or `row`

    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_31_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
    㖵
    0.46
    _
    0.42
    ים
    0.42
    لات
    0.42
    ґ
    0.42
    <0xD9>
    0.41
    וני
    0.41
    <0xEF>
    0.40
    परि
    0.40
    ց
    0.39
    POSITIVE LOGITS
     kucch
    0.54
    举办
    0.49
    ifically
    0.49
     ඔ
    0.48
    nl
    0.46
    issati
    0.46
    पयोग
    0.45
     драма
    0.45
     Potatoes
    0.45
    odată
    0.45
    Activations Density 0.002%

    No Known Activations