© 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. 94680
    Prev
    Next
    INDEX
    Explanations

    order making or time

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

    function g(x) definitions

    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
    amati
    0.50
     unsightly
    0.46
     декабря
    0.46
    琕
    0.46
    くに
    0.45
    く
    0.45
     περισ
    0.44
     όταν
    0.44
    するので
    0.44
     کنم
    0.43
    POSITIVE LOGITS
    beam
    0.49
    ------+
    0.48
    (+
    0.45
    APH
    0.44
    neau
    0.44
    ,+
    0.44
    (
    0.43
     score
    0.43
    hole
    0.43
     beats
    0.43
    Activations Density 0.001%

    No Known Activations