© 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. 10110
    Prev
    Next
    INDEX
    Explanations

    this or it is

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

    list endings and statements

    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
     정의역
    0.45
    얽
    0.39
     rohkem
    0.38
     gacchati
    0.35
     défendre
    0.35
     mennes
    0.34
    駑
    0.34
     충분
    0.34
    섦
    0.34
     যতটা
    0.33
    POSITIVE LOGITS
    这是
    0.54
     This
    0.48
    これは
    0.48
    This
    0.48
     according
    0.47
     это
    0.46
    これにより
    0.44
    according
    0.44
     говорится
    0.43
    這是
    0.43
    Activations Density 0.073%

    No Known Activations