© 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. 64019
    Prev
    Next
    INDEX
    Explanations

    roads, routes, or streets

    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
    매
    -0.88
     dekoratif
    -0.85
    μβ
    -0.85
    ovsky
    -0.84
     länder
    -0.84
     localizado
    -0.79
     induk
    -0.79
     ورز
    -0.79
    öffentlichungen
    -0.78
     annen
    -0.77
    POSITIVE LOGITS
     prowad
    0.93
     дал
    0.81
    เลือก
    0.79
     paved
    0.78
    ki
    0.78
    gendes
    0.77
    side
    0.76
     Doing
    0.75
     obtain
    0.75
     Erle
    0.74
    Activations Density 0.007%

    No Known Activations