© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49352
    Prev
    Next
    INDEX
    Explanations

    dining table and chairs

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

    multilingual tokens

    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
    ंधरा
    0.46
    醣
    0.43
    bes
    0.39
     shout
    0.39
    स्तू
    0.38
     cry
    0.38
    FundMe
    0.38
    Bes
    0.38
    MeV
    0.38
     kêu
    0.38
    POSITIVE LOGITS
     от
    0.64
    ımızı
    0.54
    จาก
    0.53
    ử
    0.52
     с
    0.52
     düz
    0.51
    ıma
    0.51
    ından
    0.50
    ıld
    0.50
    கர
    0.50
    Activations Density 0.000%

    No Known Activations