© 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. 235546
    Prev
    Next
    INDEX
    Explanations

    Denver County, harming/damaging environment, few minutes, friday

    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
    나
    0.52
    현재
    0.50
     ecclesiastical
    0.50
     SCRI
    0.49
     INDI
    0.45
     सिंचाई
    0.45
     eccles
    0.44
     february
    0.43
    아
    0.43
    <?
    0.43
    POSITIVE LOGITS
    ഗം
    0.51
     Warfare
    0.48
    वादी
    0.47
    বাদী
    0.47
    цію
    0.46
     കമ്മി
    0.46
     экономического
    0.46
    weiter
    0.45
    િમ
    0.45
    DebuggingMode
    0.45
    Activations Density 0.000%

    No Known Activations