© 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. 57824
    Prev
    Next
    INDEX
    Explanations

    Troy, Trock, Trog, Trop

    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
    ตรวจ
    -0.81
     aliento
    -0.77
    idist
    -0.76
    ेंट
    -0.72
     trachea
    -0.72
    땀
    -0.72
    Teleport
    -0.71
     criminal
    -0.71
     adequado
    -0.70
     iniciales
    -0.69
    POSITIVE LOGITS
    Paket
    0.78
     posible
    0.76
    NAG
    0.75
    <0xA3>
    0.74
    mtd
    0.74
     patterning
    0.74
    谈判
    0.73
    Renov
    0.73
    érien
    0.73
    nesc
    0.72
    Activations Density 0.035%

    No Known Activations