© 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. 57702
    Prev
    Next
    INDEX
    Explanations

    initial ViewController

    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
    initions
    -0.99
    óloga
    -0.89
    Chambers
    -0.82
     MTV
    -0.78
     gyak
    -0.76
    gridad
    -0.75
     szár
    -0.74
    ionali
    -0.74
    Faith
    -0.74
     posing
    -0.73
    POSITIVE LOGITS
    Atentamente
    0.85
    Lesley
    0.84
     Makassar
    0.83
    rizona
    0.81
     operativa
    0.78
     alterações
    0.78
    studio
    0.78
     STUDIO
    0.76
     basketball
    0.75
    alto
    0.75
    Activations Density 0.002%

    No Known Activations