© 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. 147485
    Prev
    Next
    INDEX
    Explanations

    We are

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

    who, by definition

    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
     semelhante
    0.47
     mendengar
    0.47
     unclear
    0.46
     जया
    0.45
     semelhantes
    0.45
    ânica
    0.44
     capitalismo
    0.44
    лда
    0.44
    不错
    0.43
    吞
    0.43
    POSITIVE LOGITS
     एलिमेंट्स
    0.47
     ඉ
    0.47
     فولت
    0.46
     カーボン
    0.43
     フランス
    0.43
     コー
    0.43
     ఇచ్చిన
    0.43
    voltage
    0.42
     Voltage
    0.42
     Tü
    0.42
    Activations Density 0.003%

    No Known Activations