© 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. 78046
    Prev
    Next
    INDEX
    Explanations

    actual or real implementation

    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
    izza
    -0.77
    !==
    -0.74
    igene
    -0.73
     insuper
    -0.72
    了一些
    -0.69
     WiFi
    -0.68
    making
    -0.68
     rana
    -0.68
    enums
    -0.68
     Naturschutz
    -0.68
    POSITIVE LOGITS
     actual
    0.86
    |
    0.84
     really
    0.80
    oad
    0.77
     intéress
    0.77
     sự
    0.76
    𝐄
    0.76
    utal
    0.75
    TRY
    0.75
    versations
    0.74
    Activations Density 0.006%

    No Known Activations