© 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. 177054
    Prev
    Next
    INDEX
    Explanations

    variety, condition, connections, similar

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

    past tense auxiliary verb

    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
     Конечно
    0.44
     अॅ
    0.42
     ©️
    0.41
    を中心に
    0.41
    捣
    0.40
     приложений
    0.40
     Cómo
    0.40
     Còn
    0.40
     अनि
    0.39
     এব
    0.39
    POSITIVE LOGITS
     velocities
    0.46
    quina
    0.45
    په
    0.44
     velocidades
    0.43
    idae
    0.43
    km
    0.43
    꿩
    0.43
    histos
    0.43
    했지만
    0.42
    millimeters
    0.42
    Activations Density 0.001%

    No Known Activations