© 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. 161962
    Prev
    Next
    INDEX
    Explanations

    si/sit/site

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

    siamese, sigma, side, site, sid

    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
    stieg
    0.61
    сез
    0.58
    د
    0.57
     Cag
    0.56
    zogen
    0.54
     Arz
    0.54
    ص
    0.54
    دخل
    0.54
    stufe
    0.53
    vaegir
    0.53
    POSITIVE LOGITS
     sít
    0.63
     سی
    0.61
     si
    0.61
     sig
    0.61
    1
    0.59
     situs
    0.57
    サイト
    0.56
     SIG
    0.54
    0.54
    SITE
    0.52
    Activations Density 0.311%

    No Known Activations