© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 34768
    Prev
    Next
    INDEX
    Explanations

    calculation, percentage, risk, scale

    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
     tä
    0.39
     mekan
    0.38
    ⵅ
    0.38
     adopter
    0.38
    נדה
    0.38
    sberg
    0.38
     asylum
    0.37
    loé
    0.37
    Согласно
    0.37
    ഔ
    0.37
    POSITIVE LOGITS
    select
    0.54
    others
    0.49
    only
    0.48
    possible
    0.47
    ct
    0.47
    确认
    0.46
     বাড়বে
    0.46
    better
    0.46
    顺序
    0.46
    number
    0.45
    Activations Density 0.001%

    No Known Activations