© 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. 117757
    Prev
    Next
    INDEX
    Explanations

    latitude and longitude

    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
    SuspendLayout
    -0.82
     viendra
    -0.79
    lider
    -0.76
    ianie
    -0.73
    moder
    -0.73
    envoyer
    -0.68
    Grü
    -0.66
    riezmann
    -0.66
    ="/
    -0.66
     bottle
    -0.66
    POSITIVE LOGITS
    ایج
    0.68
     Sorte
    0.66
    matite
    0.66
     prosthetic
    0.64
     caldo
    0.63
    setText
    0.63
    катерина
    0.63
    ortage
    0.62
     bolj
    0.61
     Corporations
    0.60
    Activations Density 0.037%

    No Known Activations