© 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. 63396
    Prev
    Next
    INDEX
    Explanations

    cycling and racers

    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
     fehler
    -0.87
    ilibre
    -0.86
    iales
    -0.79
     świe
    -0.78
     disk
    -0.77
     Shane
    -0.77
     Optimize
    -0.77
     Faktor
    -0.76
    ския
    -0.75
    Recharge
    -0.75
    POSITIVE LOGITS
     Sachs
    0.82
     hous
    0.74
    pagno
    0.73
    zack
    0.71
    delo
    0.71
     Commands
    0.70
     Herd
    0.70
     إلا
    0.69
    Messenger
    0.68
     昭和
    0.68
    Activations Density 0.027%

    No Known Activations