© 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. 13574
    Prev
    Next
    INDEX
    Explanations

    only,

    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
     Или
    0.46
    或者
    0.45
    或
    0.43
    ዖ
    0.43
     või
    0.42
     किंवा
    0.41
    astă
    0.41
    姩
    0.41
    在
    0.40
    在一个
    0.40
    POSITIVE LOGITS
     logros
    0.44
    others
    0.43
     حتی
    0.42
    そして
    0.42
     innumerable
    0.42
     humility
    0.41
    BURSEMENTS
    0.41
     sogar
    0.41
     وذلك
    0.40
     aliments
    0.40
    Activations Density 0.004%

    No Known Activations