© 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. 72834
    Prev
    Next
    INDEX
    Explanations

    NSC abbreviation

    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
     
    -2.88
     Easily
    -2.44
     Either
    -2.41
    A
    -2.36
     greatest
    -2.36
     Enhancing
    -2.36
     Maintaining
    -2.28
     Entering
    -2.27
     Analyzing
    -2.25
    '
    -2.23
    POSITIVE LOGITS
    ו
    2.22
     hvilket
    2.13
     outubro
    2.11
    蚡
    2.08
     karier
    2.06
    ي
    2.02
    锵
    2.00
    jangan
    1.98
    韪
    1.98
    0
    1.97
    Activations Density 0.007%

    No Known Activations