Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 15879
    Prev
    Next
    INDEX
    Explanations

    technical requirements or analysis

    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_40_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
    hement
    0.37
    ು
    0.37
    łoż
    0.36
     کل
    0.34
     ملاحظ
    0.33
     minute
    0.33
    ਹਾ
    0.33
     টানা
    0.32
     censure
    0.32
     unary
    0.32
    POSITIVE LOGITS
     T
    0.44
     TG
    0.43
    Т
    0.42
    T
    0.41
     TFS
    0.41
    𝑇
    0.41
     Т
    0.41
    𝐓
    0.40
    T
    0.40
    Tis
    0.39
    Activations Density 0.142%

    No Known Activations