© 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. 186221
    Prev
    Next
    INDEX
    Explanations

    common phrases and foreign words

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

    identifying non-English text

    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
    c
    0.51
    eb
    0.50
    ри
    0.49
    allow
    0.49
    ebles
    0.48
    un
    0.48
    eating
    0.48
    e
    0.48
    i
    0.48
    ens
    0.47
    POSITIVE LOGITS
     của
    0.56
    ຂອງ
    0.52
    。
    0.51
     exclusivos
    0.49
     dupatta
    0.49
     లే
    0.48
    স্থল
    0.47
     Terbaik
    0.47
     বললাম
    0.45
     gratuitos
    0.45
    Activations Density 0.005%

    No Known Activations