© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10621
    Prev
    Next
    INDEX
    Explanations

    shearling coats

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

    digit one

    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_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
     first
    0.61
    first
    0.61
     FIRST
    0.52
     First
    0.48
     první
    0.46
     첫
    0.46
     pierws
    0.46
     ensimmä
    0.46
     pierwszej
    0.45
    第一个
    0.45
    POSITIVE LOGITS
    ⒉
    0.77
     ২
    0.70
     ૩
    0.66
     ३
    0.65
     २
    0.65
    １
    0.64
    ３
    0.64
    ２
    0.64
    ⑤
    0.64
     ৩
    0.63
    Activations Density 0.558%

    No Known Activations