© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221118
    Prev
    Next
    INDEX
    Explanations

    tagged discussion, vb, visas, skills, detection test

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

    multi-lingual grammar basics

    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
    Negative Logits
    他的
    0.49
     appear
    0.44
    在他的
    0.41
    मा
    0.40
     contenders
    0.40
    することができます
    0.40
    ິດຕ
    0.40
    和他
    0.39
    ᅦ
    0.39
    нении
    0.39
    POSITIVE LOGITS
     ấm
    0.53
     vraag
    0.50
    okie
    0.49
     thác
    0.47
     thuế
    0.47
     thổ
    0.46
     annan
    0.46
     څه
    0.46
     ఆధ్యా
    0.46
    rien
    0.46
    Activations Density 0.001%

    No Known Activations