© 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. 59946
    Prev
    Next
    INDEX
    Explanations

    multiple kinds of sources

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

    non-English content

    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
     SAN
    0.47
    Благо
    0.46
     }}$
    0.46
     engan
    0.45
     acredito
    0.44
     á
    0.44
    Jika
    0.44
     botas
    0.44
    นัก
    0.43
    Hãy
    0.43
    POSITIVE LOGITS
     භාවිත
    0.47
    ០០
    0.47
     তুলনায়
    0.46
     পরবর্ত
    0.45
    测试
    0.45
    没有任何
    0.44
     morceau
    0.44
     কোনও
    0.43
    ﺕ
    0.43
     材料
    0.42
    Activations Density 0.000%

    No Known Activations