© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11002
    Prev
    Next
    INDEX
    Explanations

    introduces contrast or qualification

    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
    ufnahme
    -0.91
    posicao
    -0.82
     همین
    -0.77
    𝙶
    -0.77
     producciones
    -0.77
     przeci
    -0.77
    偈
    -0.77
    ullaby
    -0.76
    RatingBar
    -0.76
    HasAnnotation
    -0.74
    POSITIVE LOGITS
     actual
    1.07
     but
    0.93
    あく
    0.91
    實際
    0.91
     marino
    0.88
     tylko
    0.83
     only
    0.82
    あくまで
    0.82
    while
    0.81
    WRITE
    0.80
    Activations Density 0.063%

    No Known Activations