© 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. 2871
    Prev
    Next
    INDEX
    Explanations

    but or though

    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
     Οι
    0.31
    ↵↵
    0.30
    ویر
    0.30
     เนื่องจาก
    0.30
     İ
    0.29
     Investigations
    0.29
     Certaines
    0.29
    ാ
    0.28
     Cependant
    0.27
     The
    0.27
    POSITIVE LOGITS
     not
    0.55
     όχι
    0.45
     más
    0.43
     не
    0.42
     není
    0.41
     ikke
    0.39
    not
    0.38
    不仅仅
    0.37
     less
    0.36
     لا
    0.36
    Activations Density 0.267%

    No Known Activations