© 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. 210974
    Prev
    Next
    INDEX
    Explanations

    foreign language words followed by English

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

    look again or then

    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
    า
    0.50
    ッセージ
    0.43
    前景
    0.43
    କ
    0.43
    rishnan
    0.42
    忘
    0.42
     बगैर
    0.40
    웨어
    0.40
    ないと
    0.40
    ু
    0.40
    POSITIVE LOGITS
     ฝึก
    0.52
     legt
    0.48
     டா
    0.47
     puis
    0.46
     ወይም
    0.46
     அல்லது
    0.46
     ຫຼື
    0.46
     Postgraduate
    0.45
     பயிற்
    0.45
     คลิป
    0.45
    Activations Density 0.002%

    No Known Activations