© 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. 166802
    Prev
    Next
    INDEX
    Explanations

    adverse events, emerging markets

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

    Model Parallel Requirements

    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
    滋
    0.50
    ata
    0.47
    ர
    0.47
     จัด
    0.46
     entrar
    0.44
    ⦖
    0.44
     المنزل
    0.43
     সঠিক
    0.43
     منزل
    0.43
     作詞
    0.43
    POSITIVE LOGITS
     objectionable
    0.46
    ത്തു
    0.43
    リーブ
    0.43
    Histor
    0.42
    スポ
    0.42
     Firmware
    0.42
     repealed
    0.41
     repeatable
    0.41
    壑
    0.41
     acknowledgment
    0.41
    Activations Density 0.000%

    No Known Activations