© 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. 19445
    Prev
    Next
    INDEX
    Explanations

    numbers and slashes

    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
     There
    -2.19
     has
    -2.08
    {
    -1.68
    ESOME
    -1.68
     began
    -1.68
    ጵ
    -1.67
    attamento
    -1.66
    after
    -1.61
    ichtete
    -1.59
     would
    -1.58
    POSITIVE LOGITS
     effec
    2.03
    ``
    1.89
    的很
    1.87
    然后
    1.77
    ate
    1.75
    潆
    1.73
    CHREIBUNG
    1.70
    粜
    1.68
    ㈲
    1.68
    „
    1.67
    Activations Density 0.043%

    No Known Activations