© 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. 22-GEMMASCOPE-RES-131K
    7. 72596
    Prev
    Next
    INDEX
    Explanations

    Monroe Community College, ECT, page, comparison, Q

    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_22/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
     skak
    -1.29
    を防
    -1.21
     vernis
    -1.12
     pittores
    -1.11
     schu
    -1.09
     patate
    -1.08
     granat
    -1.07
     neder
    -1.07
     erin
    -1.05
    ДИ
    -1.05
    POSITIVE LOGITS
     irgendwann
    1.06
     abends
    0.97
    al
    0.93
    utenants
    0.93
    教科
    0.92
    icoot
    0.89
     father
    0.89
    ׳
    0.89
     zufrieden
    0.88
     传统
    0.88
    Activations Density 0.000%

    No Known Activations