© 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. 117485
    Prev
    Next
    INDEX
    Explanations

    parent child relationship

    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
    aspetto
    -0.85
    بدو
    -0.80
    ≿
    -0.80
    kinda
    -0.80
    clearly
    -0.79
     speziellen
    -0.79
    Transcriptie
    -0.79
    THANKS
    -0.79
    Transcripción
    -0.78
    yields
    -0.78
    POSITIVE LOGITS
     node
    1.64
     of
    1.33
    Node
    1.24
     nodes
    1.22
     class
    1.18
    most
    1.16
    节点
    1.10
    node
    1.07
    class
    1.05
     element
    1.05
    Activations Density 0.067%

    No Known Activations