© 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. 16866
    Prev
    Next
    INDEX
    Explanations

    CSS display block;

    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
    a
    0.48
     OF
    0.46
    려고
    0.46
    न्दर
    0.46
     क्
    0.46
    ému
    0.45
     tạm
    0.44
    न्या
    0.44
    getNumberOf
    0.44
    kich
    0.44
    POSITIVE LOGITS
    ا۔
    0.52
    ها
    0.47
     enfo
    0.44
     مقامات
    0.43
    comers
    0.42
     CDMA
    0.41
    }|
    0.41
    {
    0.40
    ައި
    0.40
    ᅢ
    0.40
    Activations Density 0.001%

    No Known Activations