© 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. 1322
    Prev
    Next
    INDEX
    Explanations

    Meagan, Meade, Miesiac, Møller

    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
    javas
    -0.69
    重
    -0.67
    &#
    -0.67
    铃
    -0.65
     għall
    -0.64
     вентиля
    -0.64
     HCM
    -0.64
     checking
    -0.63
    resh
    -0.63
    由此
    -0.62
    POSITIVE LOGITS
     upaya
    0.91
    doch
    0.76
    anja
    0.76
    barten
    0.75
    addTo
    0.74
     wherefore
    0.73
    aup
    0.73
    зия
    0.71
     глубо
    0.71
     MINING
    0.71
    Activations Density 0.017%

    No Known Activations