© 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. 183166
    Prev
    Next
    INDEX
    Explanations

    rent dumpsters or specialist care

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

    breakdown of information

    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
     实现
    0.49
     recto
    0.46
    IBILITY
    0.45
    стро
    0.45
    绘制
    0.45
    _{,
    0.44
    VIE
    0.43
    AlignedText
    0.43
     执行
    0.43
    AOrdenar
    0.43
    POSITIVE LOGITS
     speculators
    0.50
     resellers
    0.50
     Reverend
    0.50
     criminals
    0.49
     cryptocur
    0.48
    ਸ
    0.48
     submarines
    0.47
    inios
    0.47
     fundraisers
    0.46
     rapids
    0.46
    Activations Density 0.001%

    No Known Activations