© 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. 104696
    Prev
    Next
    INDEX
    Explanations

    news reporting context

    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
     these
    -1.32
     you
    -1.32
     those
    -1.25
     their
    -1.23
     такі
    -1.09
    odyear
    -1.07
    Արտաքին
    -1.06
     so
    -1.05
     more
    -1.05
     if
    -1.04
    POSITIVE LOGITS
    借助
    1.06
     ajuns
    1.05
     Meski
    1.04
    Amid
    1.02
    ILING
    1.01
    ITZER
    0.99
    Према
    0.97
     решили
    0.95
    itan
    0.95
    akei
    0.94
    Activations Density 0.001%

    No Known Activations