© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65459
    Prev
    Next
    INDEX
    Explanations

    academic citations, years

    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
     of
    -1.67
     only
    -1.60
    An
    -1.56
    You
    -1.56
     which
    -1.55
     multifaceted
    -1.55
     your
    -1.54
    了一会儿
    -1.52
     that
    -1.51
    ruckt
    -1.48
    POSITIVE LOGITS
    Methode
    1.60
     теперь
    1.56
     綺麗
    1.51
     見える
    1.48
    idlertid
    1.48
    嚷
    1.47
    Pancake
    1.47
    methode
    1.46
     EXAMPLE
    1.46
    ݁
    1.44
    Activations Density 0.010%

    No Known Activations