© 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. 108266
    Prev
    Next
    INDEX
    Explanations

    collections.deque as Queue

    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
    А
    0.56
    ﻜ
    0.55
    ్వ
    0.53
    ट
    0.50
    액
    0.49
    艨
    0.49
    િ
    0.48
    ել
    0.48
    جي
    0.48
    ايا
    0.48
    POSITIVE LOGITS
    s
    0.67
    site
    0.47
    str
    0.46
    c
    0.44
    ss
    0.44
    set
    0.43
    h
    0.43
    sett
    0.43
     Collingwood
    0.42
    lumat
    0.42
    Activations Density 0.001%

    No Known Activations