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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9129
    Prev
    Next
    INDEX
    Explanations

    multilingual continuations

    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
     بأ
    0.31
    Generation
    0.30
     केलेल्या
    0.30
     kef
    0.30
     beş
    0.30
    Range
    0.29
    τικό
    0.29
     L
    0.29
    ные
    0.29
     américaine
    0.29
    POSITIVE LOGITS
    that
    0.37
    cluding
    0.36
    爾
    0.35
    並
    0.35
    mimpi
    0.34
    katapos
    0.33
    qualiter
    0.33
    なわち
    0.33
     কিন্তু
    0.32
     পাশাপাশি
    0.32
    Activations Density 0.237%

    No Known Activations