© 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. 12566
    Prev
    Next
    INDEX
    Explanations

    toy and its associated 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_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
    ouſ
    -2.75
    
    -2.63
    踽
    -2.56
    踅
    -2.56
    NOWLEDGE
    -2.56
    ViewInit
    -2.55
    诹
    -2.53
    沕
    -2.50
    撄
    -2.48
    
    -2.48
    POSITIVE LOGITS
    The
    3.97
    1
    3.48
    the
    3.00
    Your
    2.89
    {
    2.83
    –
    2.66
     сделали
    2.66
    2
    2.58
     Are
    2.55
    する
    2.52
    Activations Density 0.002%

    No Known Activations