© 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. 85782
    Prev
    Next
    INDEX
    Explanations

    planting perennial stalking Quick

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

    definitions and examples

    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
    }\}$
    0.49
    امت
    0.47
    ט
    0.46
    痹
    0.45
    淋
    0.45
    ૦
    0.44
    ્સ
    0.43
    複雑
    0.43
    芾
    0.42
    דים
    0.42
    POSITIVE LOGITS
     spoke
    0.54
     Bakker
    0.48
     speak
    0.48
     Kaliforn
    0.47
    speak
    0.46
     speaks
    0.46
     BER
    0.46
     cla
    0.46
     posiad
    0.45
     Duan
    0.45
    Activations Density 0.000%

    No Known Activations