© 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. 232604
    Prev
    Next
    INDEX
    Explanations

    APITONG OIL, Br, DS5

    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
    ר
    0.49
     Selbst
    0.47
    媜
    0.47
     संदर्भ
    0.46
    ত্য
    0.46
    ტის
    0.45
     Organisations
    0.45
    蠡
    0.45
    이나
    0.44
    たとえば
    0.44
    POSITIVE LOGITS
     fasteners
    0.49
     latency
    0.47
     europé
    0.47
     осе
    0.46
     oysters
    0.46
     зап
    0.46
     aphids
    0.46
     with
    0.45
     immunotherapy
    0.44
     εκ
    0.44
    Activations Density 0.000%

    No Known Activations