© 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. 13556
    Prev
    Next
    INDEX
    Explanations

    or

    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
    мини
    0.41
    рожден
    0.39
    зирован
    0.38
    ेट्टी
    0.37
    哪怕
    0.36
    ﺘ
    0.36
    䂘
    0.35
    იზ
    0.35
    ฟ
    0.35
    ковой
    0.34
    POSITIVE LOGITS
     অথবা
    0.59
     hoặc
    0.54
    或其他
    0.51
     अथवा
    0.49
     veya
    0.48
     또는
    0.48
     oraz
    0.47
     அல்லது
    0.47
    したり
    0.47
     serta
    0.46
    Activations Density 0.093%

    No Known Activations