© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39089
    Prev
    Next
    INDEX
    Explanations

    Tom followed by names or compounds

    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
    也
    -2.59
     
    -2.53
     After
    -2.52
     После
    -2.42
    we
    -2.36
     Beſ
    -2.31
     That
    -2.31
    、
    -2.31
    s
    -2.22
    POSITIVE LOGITS
    釤
    3.80
    翃
    3.48
    僦
    2.67
    巂
    2.66
    亹
    2.64
     zape
    2.55
    餿
    2.53
     あります
    2.50
    畎
    2.50
    
    2.47
    Activations Density 0.021%

    No Known Activations