© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14019
    Prev
    Next
    INDEX
    Explanations

    repeated column, varying vec, repeated many

    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
    ↵↵
    -2.75
    In
    -1.74
     keď
    -1.60
    ↵↵↵
    -1.56
    
    -1.55
     många
    -1.55
    因为
    -1.50
     deinen
    -1.48
     Präsentation
    -1.48
    <bos>
    -1.47
    POSITIVE LOGITS
     for
    1.88
     sobri
    1.66
     recevrez
    1.55
     ſame
    1.52
    ですので
    1.52
    而出
    1.48
     годах
    1.47
     bouwen
    1.47
     londres
    1.45
     Сме
    1.45
    Activations Density 0.001%

    No Known Activations