© 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. 89915
    Prev
    Next
    INDEX
    Explanations

    Outstanding Company shares

    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
    或
    0.52
    时
    0.50
    ı
    0.50
     тексто
    0.46
     বা
    0.45
    ing
    0.44
    ılarak
    0.43
     или
    0.43
    Ngày
    0.43
    İ
    0.43
    POSITIVE LOGITS
     intrepid
    0.51
     costo
    0.49
     badass
    0.47
     personali
    0.46
     critters
    0.46
     artis
    0.45
     golfers
    0.45
     artista
    0.44
     gamers
    0.44
     patrocin
    0.44
    Activations Density 0.004%

    No Known Activations