© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92009
    Prev
    Next
    INDEX
    Explanations

    count of two

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بعضی
    -0.84
     некоторые
    -0.79
    同じ
    -0.75
     bestimmte
    -0.75
    きましょう
    -0.75
    bigcirc
    -0.73
     countries
    -0.73
     some
    -0.73
    Jueves
    -0.72
     многие
    -0.71
    POSITIVE LOGITS
     two
    3.55
    two
    2.83
    两个
    2.77
     three
    2.73
    兩個
    2.55
     dwóch
    2.45
     zwei
    2.38
     δύο
    2.38
     две
    2.38
    三个
    2.36
    Activations Density 0.334%

    No Known Activations