© 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. 60653
    Prev
    Next
    INDEX
    Explanations

    foreign language identifier

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

    block incoming signals

    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
    谷
    0.52
    習
    0.50
     বৃত্ত
    0.47
    об
    0.47
    но
    0.46
    هد
    0.46
    सी
    0.46
    華
    0.46
    敬
    0.46
    <0x0D>
    0.45
    POSITIVE LOGITS
    kfollowers
    0.46
     pemerintahan
    0.45
     afară
    0.44
     mua
    0.43
    お客
    0.43
    ऊन
    0.43
     çıkarm
    0.43
    )|^
    0.42
     کوئی
    0.42
    lepas
    0.41
    Activations Density 0.000%

    No Known Activations