© 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. 128214
    Prev
    Next
    INDEX
    Explanations

    relates to description

    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
     through
    -1.91
     using
    -1.69
     of
    -1.68
     by
    -1.67
     from
    -1.61
     without
    -1.60
    🌱
    -1.45
     帳
    -1.42
     on
    -1.38
     Compared
    -1.38
    POSITIVE LOGITS
    暑い
    1.70
    寒い
    1.68
    냑
    1.62
    
    1.60
    놋
    1.55
    いよいよ
    1.55
    졍
    1.52
    primarily
    1.51
    sthe
    1.50
    Groet
    1.50
    Activations Density 0.150%

    No Known Activations