© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11229
    Prev
    Next
    INDEX
    Explanations

    the number one

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

    one partner

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

    say one

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
     SINGLE
    0.47
     single
    0.43
    單
    0.43
    単
    0.42
    single
    0.41
     Single
    0.41
    单
    0.41
    那些
    0.40
    Single
    0.40
     qualsiasi
    0.40
    POSITIVE LOGITS
     one
    2.91
     один
    2.41
     одну
    2.33
    หนึ่ง
    2.31
     одного
    2.28
     одна
    2.25
     yksi
    2.25
     satu
    2.16
     одной
    2.13
     하나
    2.09
    Activations Density 0.519%

    No Known Activations