© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103231
    Prev
    Next
    INDEX
    Explanations

    york and new york

    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
    
    -3.19
    稣
    -2.98
    งิน
    -2.73
    咴
    -2.69
    鱨
    -2.61
    ・・・。
    -2.59
    
    -2.55
     så
    -2.55
    鲎
    -2.52
    笵
    -2.44
    POSITIVE LOGITS
    or
    2.91
    o
    2.64
    9
    2.56
    out
    2.45
    We
    2.44
    h
    2.41
    If
    2.39
    ork
    2.30
    2
    2.30
     способ
    2.28
    Activations Density 0.010%

    No Known Activations