© 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. 9268
    Prev
    Next
    INDEX
    Explanations

    predicting noise

    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
    できません
    0.44
    ப்பதற்காக
    0.44
     IOException
    0.43
     &/
    0.42
     TypeError
    0.42
    不了
    0.41
     monoton
    0.41
     কিংবা
    0.41
    ーフ
    0.41
    >×</
    0.41
    POSITIVE LOGITS
     २०२
    0.52
     २०२२
    0.50
     ২০২৩
    0.48
     newborns
    0.46
     เริ่ม
    0.45
    sembles
    0.44
     semiconductors
    0.44
     është
    0.44
    تهي
    0.44
     symptômes
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.