© 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. 890
    Prev
    Next
    INDEX
    Explanations

    pointers to common types

    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
    .
    -2.33
     are
    -2.13
     
    -1.95
     It
    -1.69
     obtend
    -1.57
    …
    -1.48
     permanece
    -1.43
     probablemente
    -1.41
    .
    -1.38
     if
    -1.36
    POSITIVE LOGITS
    استفاده
    2.00
    ៚
    1.98
    ניתן
    1.92
    ⤹
    1.79
     水墨
    1.76
    俢
    1.76
     ftate
    1.70
     palsu
    1.70
     jūs
    1.69
    Recht
    1.68
    Activations Density 0.002%

    No Known Activations