© 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. 105349
    Prev
    Next
    INDEX
    Explanations

    all the

    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
    any
    -1.60
     in
    -1.55
     is
    -1.49
    now
    -1.43
    ED
    -1.38
     dataSnapshot
    -1.38
     majority
    -1.34
    for
    -1.33
    es
    -1.30
    
    -1.30
    POSITIVE LOGITS
    Ultimately
    1.36
    岁月
    1.27
    ﾋ
    1.27
     deliciosos
    1.27
     régi
    1.21
    Ваш
    1.21
     Ultimately
    1.19
     damaged
    1.19
     roused
    1.18
    initialization
    1.18
    Activations Density 0.014%

    No Known Activations