© 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. 75456
    Prev
    Next
    INDEX
    Explanations

    dormant and defunct

    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
     wenigen
    -2.56
    
    -2.52
    谖
    -2.50
    絝
    -2.48
    鐒
    -2.44
     عندما
    -2.42
    蔸
    -2.41
     самая
    -2.41
    archiwizowane
    -2.30
     \"
    -2.23
    POSITIVE LOGITS
    ,”
    3.16
    ↵
    2.55
    !』
    2.36
    ,…
    2.31
     for
    2.31
    This
    2.30
     ditemui
    2.25
     in
    2.20
     These
    2.20
    AN
    2.14
    Activations Density 0.004%

    No Known Activations