© 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. 13018
    Prev
    Next
    INDEX
    Explanations

    words followed by counts

    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
     '
    -1.63
     This
    -1.52
    مسلسل
    -1.44
    To
    -1.42
     in
    -1.38
    Who
    -1.37
    ஂ
    -1.30
     ogni
    -1.29
    
    -1.27
    Where
    -1.25
    POSITIVE LOGITS
     these
    1.85
     their
    1.63
     recent
    1.62
     certain
    1.61
     recently
    1.60
     our
    1.59
     what
    1.59
    妧
    1.56
     such
    1.55
     meisje
    1.49
    Activations Density 0.115%

    No Known Activations