© 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-65K
    4. 20111
    Prev
    Next
    INDEX
    Explanations

    exponentiation in formulas

    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_65k_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
     Schae
    0.44
     выбора
    0.41
     Cushion
    0.40
    আমাকে
    0.40
     Retention
    0.40
    إ
    0.40
    א
    0.38
    ૧
    0.37
    ontal
    0.37
    icam
    0.37
    POSITIVE LOGITS
     keny
    0.39
    ற்றிய
    0.37
    jasama
    0.37
     সব
    0.37
    䙷
    0.36
     akhir
    0.36
     finalist
    0.36
    スマート
    0.36
    ಲಾಗುತ್ತದೆ
    0.35
    ুখ
    0.35
    Activations Density 0.001%

    No Known Activations