© 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-65K
    7. 2075
    Prev
    Next
    INDEX
    Explanations

    math results in boxes

    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_65k_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
    ry
    0.49
    <0x0D>
    0.44
     spotting
    0.43
     ín
    0.39
    re
    0.38
     pitting
    0.38
    ty
    0.38
    annya
    0.37
    sw
    0.36
     Couples
    0.36
    POSITIVE LOGITS
    মনসিংহ
    0.44
    狷
    0.42
    Besch
    0.42
    ofthe
    0.41
    ק
    0.39
    滏
    0.39
    تون
    0.39
    ת
    0.39
    логи
    0.38
    ង់
    0.38
    Activations Density 0.002%

    No Known Activations