© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70814
    Prev
    Next
    INDEX
    Explanations

    units of measure

    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
     crucial
    -0.89
    ;++
    -0.79
     doesn
    -0.79
    われて
    -0.78
     pivotal
    -0.78
     कौन
    -0.77
     part
    -0.76
    roscopy
    -0.75
     ряд
    -0.75
     اپنے
    -0.75
    POSITIVE LOGITS
     of
    1.35
     during
    1.12
    !」
    1.05
     when
    1.03
    unitPattern
    0.96
     terlaris
    0.96
     cathédrale
    0.95
    romyal
    0.95
     sorprendió
    0.94
    !";
    0.94
    Activations Density 0.025%

    No Known Activations