© 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. 48535
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    defining rules or purpose

    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
    Governor
    0.50
     ((
    0.50
    鰭
    0.49
     ហើយ
    0.48
     governorship
    0.47
     regering
    0.47
    kule
    0.47
    ulu
    0.46
     حكوم
    0.46
    =".$
    0.46
    POSITIVE LOGITS
    ‌اند
    0.47
    プーン
    0.44
     Wolfgang
    0.43
     창
    0.42
     لنک
    0.42
     важли
    0.41
    ్రమ
    0.41
    िवार
    0.41
    हरे
    0.41
     Jonny
    0.41
    Activations Density 0.000%

    No Known Activations