© 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. 99845
    Prev
    Next
    INDEX
    Explanations

    call us to arrange

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

    sports goals and viewership

    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
     ofrecer
    0.47
     காமெ
    0.46
    дцать
    0.45
     especificar
    0.44
     சதவீ
    0.44
    (../
    0.44
     yanlış
    0.44
     შემთ
    0.44
     או
    0.43
     ყველ
    0.43
    POSITIVE LOGITS
     Maritime
    0.55
     Collingwood
    0.46
     Н
    0.44
     NK
    0.44
     KOH
    0.44
     roaring
    0.44
     Praha
    0.44
     Brewery
    0.44
     Triangular
    0.44
    Tottenham
    0.44
    Activations Density 0.001%

    No Known Activations