© 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. 59946
    Prev
    Next
    INDEX
    Explanations

    numbers and timestamps

    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
     unſ
    -1.52
    悫
    -1.41
     治療
    -1.39
    nowa
    -1.39
     största
    -1.36
    
    -1.35
    ֊
    -1.35
     spannend
    -1.31
     пришли
    -1.30
    镡
    -1.30
    POSITIVE LOGITS
     is
    1.91
     -
    1.43
     +
    1.35
     has
    1.31
     can
    1.31
     could
    1.30
     had
    1.28
    i
    1.26
     vient
    1.26
    .
    1.26
    Activations Density 0.017%

    No Known Activations