© 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. 132234
    Prev
    Next
    INDEX
    Explanations

    © 2013

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

    conditional generation levels

    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
    ⟤
    0.59
    昅
    0.55
     conclusiones
    0.54
     ตาย
    0.52
     विभाजन
    0.52
     bahis
    0.51
     πίνακα
    0.51
     ถนน
    0.51
    矨
    0.51
    тности
    0.50
    POSITIVE LOGITS
    the
    0.58
    ↵
    0.54
    4
    0.54
    Xc
    0.52
    list
    0.51
    itz
    0.50
    our
    0.49
    The
    0.48
    get
    0.47
     the
    0.47
    Activations Density 0.001%

    No Known Activations