© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46313
    Prev
    Next
    INDEX
    Explanations

    foreign negation or Slavic/Germanic languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    打開
    0.44
    或許
    0.42
     rápidos
    0.41
     hurriedly
    0.41
    はよう
    0.40
    鍘
    0.40
     loopholes
    0.39
     скажу
    0.39
    甚至是
    0.38
     escond
    0.38
    POSITIVE LOGITS
     не
    0.55
     nicht
    0.53
    Nicht
    0.52
    nicht
    0.50
    ис
    0.50
    ที่ไม่
    0.49
     Nicht
    0.48
     к
    0.48
     т
    0.47
     non
    0.46
    Activations Density 0.002%

    No Known Activations