© 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. 170037
    Prev
    Next
    INDEX
    Explanations

    page numbers, chapter titles

    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
     бі
    0.57
    𝓟
    0.54
    linkCell
    0.50
     הל
    0.49
     الشمال
    0.49
    Соцмережа
    0.48
    ಗೋ
    0.48
     دی
    0.48
     ವ್ಯಾ
    0.48
     Adriatic
    0.48
    POSITIVE LOGITS
    >
    0.49
     Page
    0.44
    বহ
    0.44
    Expect
    0.41
     pages
    0.41
     простой
    0.39
    Chapter
    0.39
     Pages
    0.39
    Willow
    0.38
    iance
    0.38
    Activations Density 0.000%

    No Known Activations