© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3051
    Prev
    Next
    INDEX
    Explanations

    definitions, types, concepts

    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_16k_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
    ロ
    0.42
    スク
    0.42
    ات
    0.39
    -
    0.38
    락
    0.38
    ＰＥＮＡＮＡ
    0.38
    كي
    0.38
    향
    0.37
    娜
    0.37
    ┄
    0.37
    POSITIVE LOGITS
     Definition
    0.47
    types
    0.47
     CGI
    0.44
    duğu
    0.43
     मुताब
    0.43
     त्यांची
    0.43
    monotonic
    0.43
    ilibrium
    0.43
     सम्बन्ध
    0.42
    ell
    0.42
    Activations Density 0.034%

    No Known Activations