© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48318
    Prev
    Next
    INDEX
    Explanations

    introduces specific aspects

    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
     then
    -1.96
     пройдет
    -1.48
    two
    -1.42
    gelöst
    -1.41
     będ
    -1.41
    geführt
    -1.41
     nadru
    -1.41
    黑衣
    -1.40
     nevera
    -1.38
     vodou
    -1.38
    POSITIVE LOGITS
     to
    1.87
     their
    1.82
     a
    1.73
     that
    1.70
     do
    1.63
     vielleicht
    1.58
     bazı
    1.54
     produce
    1.49
     on
    1.48
    があります
    1.46
    Activations Density 20.543%

    No Known Activations