© 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. 112519
    Prev
    Next
    INDEX
    Explanations

    FAA, scheduler, seismic shifts

    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
    s
    -2.63
    禟
    -2.36
    憷
    -2.33
    僰
    -2.23
    fting
    -2.23
    亖
    -2.19
    尨
    -2.16
    殽
    -2.13
    “
    -2.13
    ″
    -2.11
    POSITIVE LOGITS
    {
    2.97
    >
    2.83
    ',
    2.34
    釭
    2.28
     If
    2.25
    婬
    2.14
    僊
    2.02
    窳
    1.99
     knows
    1.94
    ၟ
    1.94
    Activations Density 0.001%

    No Known Activations