© 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. 170416
    Prev
    Next
    INDEX
    Explanations

    of productivity

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

    recent or past events

    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
     हिंदुस्तान
    0.46
    -
    0.44
     faq
    0.43
     shipyard
    0.43
     teenager
    0.42
    พูด
    0.42
     carab
    0.42
     lottery
    0.41
     cem
    0.41
    യ്‌
    0.40
    POSITIVE LOGITS
    锡
    0.54
     الاد
    0.52
    gı
    0.52
    鋯
    0.52
    orElse
    0.49
     έγ
    0.49
    锆
    0.49
    ieck
    0.48
    䥑
    0.47
    də
    0.47
    Activations Density 0.000%

    No Known Activations