© 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. 14263
    Prev
    Next
    INDEX
    Explanations

    negative concepts or descriptions

    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
    I
    -2.03
     Some
    -1.91
    atação
    -1.88
                
    -1.82
    ฬ
    -1.81
     akin
    -1.77
    私には
    -1.75
     剤
    -1.72
    Some
    -1.70
    andowski
    -1.66
    POSITIVE LOGITS
    ↵
    2.39
    閦
    1.93
     zwart
    1.90
     nowy
    1.86
     samego
    1.81
     donker
    1.79
     totalmente
    1.71
    ve
    1.69
    
    1.67
     pozycji
    1.66
    Activations Density 0.009%

    No Known Activations