© 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. 167646
    Prev
    Next
    INDEX
    Explanations

    withholding taxes, LB position

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

    describing potential future scenarios

    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
     Música
    0.50
     músicas
    0.50
    ข้อมูล
    0.47
    頭髮
    0.47
     dientes
    0.47
    脏
    0.47
    вата
    0.47
    गौरतलब
    0.45
    倬
    0.45
    』（
    0.45
    POSITIVE LOGITS
     recognized
    0.55
     sculptor
    0.53
     prospecting
    0.52
     aspiring
    0.52
     nugget
    0.52
     sculptural
    0.50
     internally
    0.50
     brewery
    0.49
     hypoallergenic
    0.49
     prerequisite
    0.47
    Activations Density 0.001%

    No Known Activations