© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86140
    Prev
    Next
    INDEX
    Explanations

    words after punctuation

    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
    齪
    -1.91
     then
    -1.85
     therefore
    -1.45
     something
    -1.44
     doivent
    -1.43
    
    -1.43
    こっち
    -1.42
    侂
    -1.39
    EVERY
    -1.39
     spektak
    -1.37
    POSITIVE LOGITS
     with
    2.31
     from
    2.02
     without
    1.93
     for
    1.84
     as
    1.83
     by
    1.81
     or
    1.74
     on
    1.58
     during
    1.55
     igjen
    1.52
    Activations Density 0.061%

    No Known Activations