© 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. 143350
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    language analysis

    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
    Par
    0.57
     par
    0.54
    Nous
    0.49
     distinct
    0.47
    "+
    0.47
     sugest
    0.47
     deles
    0.46
    for
    0.45
    Map
    0.45
    တို့
    0.44
    POSITIVE LOGITS
    賺
    0.46
    lán
    0.46
    奀
    0.44
    㳑
    0.43
    مس
    0.42
    لم
    0.42
    目に
    0.41
    忶
    0.41
    estä
    0.41
    त्या
    0.41
    Activations Density 0.000%

    No Known Activations