© 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. 22-GEMMASCOPE-RES-131K
    7. 25713
    Prev
    Next
    INDEX
    Explanations

    surprise and secret actions

    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
    écrire
    -0.88
     ISTAT
    -0.86
    
    -0.84
    いま
    -0.83
     若い
    -0.83
     volgende
    -0.81
    ذ
    -0.81
     مم
    -0.81
     chanh
    -0.80
    ator
    -0.79
    POSITIVE LOGITS
     surprise
    2.17
    surprise
    1.84
     Surprise
    1.80
    Surprise
    1.68
     surprises
    1.68
     unexpected
    1.66
     sudden
    1.65
     sorpresa
    1.45
     abrupt
    1.34
     unprepared
    1.34
    Activations Density 0.068%

    No Known Activations