© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58997
    Prev
    Next
    INDEX
    Explanations

    part of programming, legal cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comunicación
    -0.87
    ää
    -0.81
    varargin
    -0.81
    Synopsis
    -0.79
    演技
    -0.78
    rijving
    -0.78
     performers
    -0.78
     färg
    -0.77
    żenia
    -0.77
    мое
    -0.76
    POSITIVE LOGITS
     wartet
    0.86
     tree
    0.84
     Indicate
    0.83
     навіть
    0.82
     vlog
    0.82
    ytä
    0.80
    两个人
    0.80
    かね
    0.76
    tree
    0.76
    relsen
    0.76
    Activations Density 0.001%

    No Known Activations