© 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. 65595
    Prev
    Next
    INDEX
    Explanations

    what i like about

    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
    ,"
    -1.99
     more
    -1.83
     brought
    -1.69
    戩
    -1.67
     made
    -1.66
    EdgeInsets
    -1.55
     to
    -1.54
     multitude
    -1.53
     был
    -1.51
    štění
    -1.48
    POSITIVE LOGITS
     seolah
    1.59
     éché
    1.56
    2
    1.55
     siè
    1.54
    cjach
    1.53
    3
    1.53
     chè
    1.52
     eer
    1.51
     এবং
    1.50
    6
    1.50
    Activations Density 0.008%

    No Known Activations