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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64212
    Prev
    Next
    INDEX
    Explanations

    diamond geezer

    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
     inflammation
    -0.74
    ční
    -0.73
    Imaginary
    -0.71
     किसी
    -0.71
     genetics
    -0.70
     As
    -0.69
    关
    -0.69
    modities
    -0.68
     ध
    -0.68
    葦
    -0.68
    POSITIVE LOGITS
     dreadful
    0.79
     Temperatures
    0.77
    tiendo
    0.77
    alya
    0.76
    ifera
    0.76
    icei
    0.75
    몄
    0.75
    annah
    0.73
     detalhe
    0.73
    pagation
    0.73
    Activations Density 0.020%

    No Known Activations