© 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. 189939
    Prev
    Next
    INDEX
    Explanations

    anticipate, may, intend, plan

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

    function calls and script commands

    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
    褐
    0.40
    libp
    0.39
     природ
    0.39
     বাণিজ্য
    0.39
    upon
    0.38
    ᱢ
    0.38
     Fortress
    0.38
    传感器
    0.38
    皰
    0.38
    mmol
    0.37
    POSITIVE LOGITS
     activate
    0.60
     activates
    0.47
    ();
    0.46
    ()
    0.46
     obtenir
    0.46
     først
    0.45
     activating
    0.45
     svih
    0.45
    ())->
    0.44
     initialize
    0.43
    Activations Density 0.000%

    No Known Activations