© 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. 26116
    Prev
    Next
    INDEX
    Explanations

    Measuring Brain Stimulation

    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
     their
    -1.18
    でしたが
    -1.11
     them
    -1.11
     both
    -1.08
     that
    -1.05
     strategia
    -1.05
    fokus
    -1.03
    ارس
    -1.02
    windigkeit
    -1.00
     cumpleaños
    -0.98
    POSITIVE LOGITS
    though
    1.29
    скій
    1.15
     '.';
    1.09
    tablissements
    1.07
     wondrous
    1.02
    还可以
    1.01
    êtements
    1.00
    mon
    0.95
    is
    0.95
    O
    0.95
    Activations Density 0.000%

    No Known Activations