© 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. 3802
    Prev
    Next
    INDEX
    Explanations

    football, coco, exams

    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
    3
    0.53
     en
    0.50
     Dot
    0.50
     diffé
    0.50
     owner
    0.48
     loin
    0.48
     dot
    0.48
     hydroxy
    0.48
    的天
    0.47
     cend
    0.47
    POSITIVE LOGITS
     радика
    0.46
    坊
    0.45
    canceled
    0.44
    acharya
    0.44
    ાવો
    0.43
    чи
    0.42
    фов
    0.42
    嘲
    0.42
    訝
    0.42
    徘
    0.42
    Activations Density 0.000%

    No Known Activations