© 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. 4084
    Prev
    Next
    INDEX
    Explanations

    author names after by

    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
     caoutch
    0.43
     ít
    0.40
     måde
    0.37
     avem
    0.37
     seasonings
    0.36
    ায়ত্ত
    0.35
    👍
    0.35
     পাবেন
    0.35
    ᓲ
    0.34
    ayvachi
    0.34
    POSITIVE LOGITS
     |
    0.44
     DEPARTMENT
    0.41
     MEETING
    0.40
    ↵
    0.38
     Theatre
    0.38
     Department
    0.38
     Proposed
    0.38
     Testimony
    0.38
     तिथि
    0.38
     Т
    0.38
    Activations Density 0.137%

    No Known Activations