© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42723
    Prev
    Next
    INDEX
    Explanations

    what does this mean

    np_acts-logits-general · gemini-2.5-flash-lite

    breath and stories described

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ૩
    0.51
     ব্যতিক্রম
    0.49
     precursors
    0.47
     perennials
    0.47
     libraries
    0.46
     بسیاری
    0.46
     ischemia
    0.45
     wyjątk
    0.45
     tributaries
    0.45
     bioqu
    0.45
    POSITIVE LOGITS
    ًا
    0.58
    짓
    0.52
    ਆ
    0.49
    Eh
    0.45
    antal
    0.44
    챈
    0.44
    日本
    0.44
    訲
    0.43
    贊
    0.43
     समझौ
    0.43
    Activations Density 0.001%

    No Known Activations