© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76753
    Prev
    Next
    INDEX
    Explanations

    royal albert hall england

    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
     Lash
    -0.91
    JF
    -0.72
    APR
    -0.71
    orca
    -0.69
     Camin
    -0.68
    contin
    -0.68
    Connection
    -0.68
     аген
    -0.66
    çam
    -0.66
    finity
    -0.66
    POSITIVE LOGITS
     програ
    0.72
     quirk
    0.69
     kropp
    0.68
    toxic
    0.66
     owning
    0.65
     sostanze
    0.65
     calculated
    0.64
     chaps
    0.63
     collections
    0.63
     饰
    0.63
    Activations Density 0.053%

    No Known Activations