© 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. 112241
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and ingredients

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

    if something happens

    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
     flexing
    0.43
    咲
    0.40
    vastatin
    0.39
     molécules
    0.37
    ൊപ്പം
    0.36
     profiles
    0.35
     CEC
    0.35
     ancillary
    0.34
    MacroExpansion
    0.34
     bont
    0.34
    POSITIVE LOGITS
    ل
    0.52
    น
    0.52
     entfernt
    0.51
    ۱
    0.48
    డయ
    0.46
     Campground
    0.46
    이나
    0.46
    endlich
    0.46
    ואה
    0.46
    灲
    0.45
    Activations Density 0.001%

    No Known Activations