© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 477
    Prev
    Next
    INDEX
    Explanations

    mentioning other languages

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

    entrepreneurial vision</word>

    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
    !)
    0.46
    怎么办
    0.43
    !,
    0.42
    Simply
    0.42
    ,+
    0.41
     efficiently
    0.41
    {
    0.41
    .)
    0.41
    Rock
    0.40
    Christian
    0.40
    POSITIVE LOGITS
     महे
    0.54
     خوش
    0.52
    encerramento
    0.52
     ronde
    0.48
    鿁
    0.48
     encir
    0.47
    annonce
    0.47
    その他
    0.46
    tarif
    0.46
     جهانی
    0.45
    Activations Density 0.000%

    No Known Activations