© 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. 106513
    Prev
    Next
    INDEX
    Explanations

    academic licenses and libraries

    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
    Start
    -0.77
     Start
    -0.69
    プーン
    -0.69
    voll
    -0.68
    start
    -0.68
     球
    -0.67
    ph
    -0.67
    ケティング
    -0.67
    bule
    -0.66
    marker
    -0.66
    POSITIVE LOGITS
    Zad
    0.65
     loamy
    0.63
    живание
    0.63
    setViewport
    0.62
     sø
    0.62
    foil
    0.62
     Tower
    0.62
    rouwen
    0.61
    zad
    0.61
    Statics
    0.60
    Activations Density 0.085%

    No Known Activations