© 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. 10-GEMMASCOPE-RES-131K
    7. 45270
    Prev
    Next
    INDEX
    Explanations

    AuthService, getPosition, Rye, Pb, euth, Musa, Fayetteville

    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_10/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
    which
    -3.34
    那我
    -3.33
    S
    -2.98
    t
    -2.86
     WHICH
    -2.83
     voor
    -2.80
    la
    -2.75
    ㌀
    -2.72
    ay
    -2.69
    ي
    -2.67
    POSITIVE LOGITS
     \&
    2.55
     ‘
    2.50
    vantaged
    2.31
    可能是
    2.28
    moteur
    2.25
    縈
    2.16
     帅气
    2.06
     crumbling
    2.03
     Focusing
    2.00
    We
    1.98
    Activations Density 0.004%

    No Known Activations