© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9920
    Prev
    Next
    INDEX
    Explanations

    reporting sayings and feelings

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

    particles and grammatical endings

    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_40_width_16k_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
    透過
    0.49
     ಮೂಲಕ
    0.47
    ／
    0.46
    ：
    0.46
    規劃
    0.44
    矚
    0.44
    全程
    0.44
     ：
    0.43
    ＋
    0.43
    另一
    0.43
    POSITIVE LOGITS
    そういう
    0.70
    すごい
    0.58
     まあ
    0.57
    왤
    0.54
    こういう
    0.53
    美味しい
    0.53
    というか
    0.52
    すごく
    0.52
    くらいの
    0.51
    ぐらい
    0.50
    Activations Density 0.044%

    No Known Activations