© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116820
    Prev
    Next
    INDEX
    Explanations

    MATLAB numerical operations

    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
     второго
    -0.78
    argu
    -0.77
    tivité
    -0.71
     Fahrt
    -0.71
    ()`
    -0.71
    对
    -0.70
     garantiert
    -0.69
    enjoy
    -0.69
    cipy
    -0.68
     recommande
    -0.67
    POSITIVE LOGITS
     reshape
    1.25
     squeeze
    1.06
     cat
    1.04
     double
    0.99
    double
    0.98
     transpose
    0.94
    reshape
    0.93
     ones
    0.93
    squeeze
    0.90
     circ
    0.89
    Activations Density 0.014%

    No Known Activations