© 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. 82809
    Prev
    Next
    INDEX
    Explanations

    Samsung Pay, WordPress, compose, spiked, PCBs

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

    quantifier phrase followed by noun

    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
     coward
    0.50
     manoeuvre
    0.47
     让
    0.46
    PatientR
    0.46
     他们
    0.45
     besie
    0.44
     Jacob
    0.44
     PROCEDURE
    0.43
    㫣
    0.43
     jullie
    0.43
    POSITIVE LOGITS
    regierung
    0.48
     biographical
    0.47
     بجلی
    0.47
    стей
    0.45
    ставка
    0.45
    हूं
    0.45
    молу
    0.45
    لیکن
    0.44
    дық
    0.44
    ون
    0.44
    Activations Density 0.002%

    No Known Activations