© 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. 205882
    Prev
    Next
    INDEX
    Explanations

    it all

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

    reliability and doing things

    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
    NCIA
    0.52
     escritório
    0.49
    ᆭ
    0.49
     iconos
    0.48
     الحكم
    0.48
     ordenador
    0.47
     acrescent
    0.47
     fato
    0.46
     analisa
    0.46
    艳
    0.45
    POSITIVE LOGITS
    栘
    0.47
    ุงเทพ
    0.46
     주인공
    0.44
    lod
    0.44
    kus
    0.44
     अथ
    0.43
    lant
    0.43
     よ
    0.42
    ///////////
    0.42
    🍧
    0.42
    Activations Density 0.001%

    No Known Activations