© 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. 192498
    Prev
    Next
    INDEX
    Explanations

    phrases and descriptions

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

    two people

    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
    TypeId
    0.48
     حكوم
    0.46
     Kiến
    0.46
     সরকারের
    0.46
     FGD
    0.46
     Размер
    0.46
    ியோ
    0.45
     Đình
    0.45
     அளித்த
    0.45
    挝
    0.45
    POSITIVE LOGITS
     independ
    0.47
    <0x80>
    0.46
     ข้อ
    0.44
    張
    0.44
    cha
    0.43
    cca
    0.43
    map
    0.43
    anj
    0.42
    mapper
    0.41
    dna
    0.41
    Activations Density 0.000%

    No Known Activations