© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45717
    Prev
    Next
    INDEX
    Explanations

    Japanese and Korean particles

    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_65k_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
     to
    0.54
    érer
    0.53
    <h2>
    0.52
    to
    0.51
     있다면
    0.50
     때는
    0.50
     hvis
    0.49
     rencontrer
    0.46
    Quando
    0.46
     부분을
    0.46
    POSITIVE LOGITS
     không
    0.70
    不會
    0.66
    с
    0.64
     not
    0.63
    வதில்லை
    0.60
    決して
    0.60
    は
    0.60
    できません
    0.59
    基本的に
    0.58
    не
    0.58
    Activations Density 0.002%

    No Known Activations