© 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. 10-GEMMASCOPE-RES-131K
    4. 119574
    Prev
    Next
    INDEX
    Explanations

    background, ideology, spouse, or business

    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
    ($__
    -1.32
     utop
    -1.26
    ?»
    -1.26
    ']").
    -1.26
    !»
    -1.25
     susc
    -1.23
     constater
    -1.23
    ğan
    -1.23
     protocole
    -1.23
    >';
    
    -1.20
    POSITIVE LOGITS
     which
    2.00
     that
    1.99
     or
    1.73
     different
    1.65
     there
    1.57
     maravillosas
    1.56
    又は
    1.38
     but
    1.34
     to
    1.34
     you
    1.34
    Activations Density 0.090%

    No Known Activations