© 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. 119585
    Prev
    Next
    INDEX
    Explanations

    _id, _body, _index, _info, $kind

    np_acts-logits-general · gemini-2.5-flash-lite

    underscore characters, particularly in variable names and object properties in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    誰でも
    -1.50
    㩒
    -1.48
    𐐀
    -1.47
     than
    -1.46
    </strong>
    -1.45
     frequentemente
    -1.45
     suivent
    -1.44
    諷
    -1.43
    
    -1.41
     pensent
    -1.39
    POSITIVE LOGITS
    现在的
    1.54
     d
    1.52
     ''
    1.51
    Y
    1.49
    .......
    1.48
     !(
    1.48
     cautious
    1.46
    Some
    1.46
     m
    1.45
    ........
    1.44
    Activations Density 0.007%

    No Known Activations