© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109783
    Prev
    Next
    INDEX
    Explanations

    between languages and concepts

    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
    .
    0.49
    0.43
    urement
    0.42
     ju
    0.42
     situation
    0.42
    '
    0.41
     predators
    0.41
    (
    0.40
    "
    0.40
     silos
    0.39
    POSITIVE LOGITS
    лена
    0.55
     станда
    0.51
    ৮
    0.50
     માતા
    0.50
    ת
    0.49
     мм
    0.49
     pptd
    0.49
     વર્ષ
    0.49
    ل
    0.48
    ৯
    0.47
    Activations Density 0.005%

    No Known Activations