© 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. 76921
    Prev
    Next
    INDEX
    Explanations

    as break the

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

    after prepositions

    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
    rač
    0.52
    슐
    0.46
     brightly
    0.45
     bột
    0.44
    arlene
    0.44
    Neutral
    0.44
    ziert
    0.44
     उद्घाटन
    0.43
    ledovatel
    0.43
    ıma
    0.43
    POSITIVE LOGITS
     embarrass
    0.48
    还有
    0.48
    textBox
    0.47
     éton
    0.47
    ลัง
    0.46
    น
    0.46
    มัน
    0.46
     سری
    0.45
     yeh
    0.45
     are
    0.45
    Activations Density 0.003%

    No Known Activations