© 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. 1230
    Prev
    Next
    INDEX
    Explanations

    explanation

    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
     itd
    0.49
    ん
    0.48
     উদ্বেগ
    0.46
    𝓭
    0.46
    ັ
    0.46
     veryvery
    0.45
     অস্থির
    0.44
    ۵
    0.44
     naquele
    0.43
    ۴
    0.43
    POSITIVE LOGITS
    a
    0.46
     Klinik
    0.46
     channels
    0.44
     setups
    0.44
     чином
    0.44
     Algorithm
    0.43
    कर्ता
    0.43
     Caballero
    0.43
     prof
    0.43
     Apparel
    0.42
    Activations Density 0.000%

    No Known Activations