© 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. 22-GEMMASCOPE-RES-131K
    7. 13640
    Prev
    Next
    INDEX
    Explanations

    quotes and introductory words

    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
     as
    -1.83
     with
    -1.76
     on
    -1.58
     so
    -1.56
     just
    -1.48
    ....
    -1.48
    .......
    -1.46
    ......
    -1.46
    !!
    -1.41
    .....
    -1.41
    POSITIVE LOGITS
    傒
    1.59
     éte
    1.56
     spéciaux
    1.52
     effici
    1.51
     charlotte
    1.47
    ︲
    1.45
    ילום
    1.45
    瓛
    1.45
     languid
    1.45
     interrom
    1.43
    Activations Density 0.057%

    No Known Activations