© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75170
    Prev
    Next
    INDEX
    Explanations

    opening files with "r", "w", or "rb"

    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_22/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
     of
    -2.20
     to
    -1.99
     by
    -1.70
     have
    -1.66
     that
    -1.60
     from
    -1.46
    //!
    
    -1.43
     who
    -1.41
     the
    -1.38
     know
    -1.37
    POSITIVE LOGITS
    Karena
    1.43
     espalda
    1.35
     mélang
    1.32
    laag
    1.30
    差别
    1.30
     maniere
    1.30
    我們
    1.30
     réve
    1.29
    گروه
    1.27
    谕
    1.27
    Activations Density 0.001%

    No Known Activations