© 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. 34-GEMMASCOPE-RES-131K
    7. 57984
    Prev
    Next
    INDEX
    Explanations

    find it amazing

    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_34/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
    🫤
    -0.81
    
    -0.80
     inesperado
    -0.76
     ponemos
    -0.75
     verändert
    -0.75
     ruedas
    -0.74
     parecido
    -0.73
     gustan
    -0.71
    Uncertainty
    -0.70
    ometre
    -0.69
    POSITIVE LOGITS
     amazed
    2.56
     amaz
    2.47
     amazement
    2.38
     amaze
    2.28
     astonishment
    2.06
     aston
    2.02
    amaz
    1.93
     baffled
    1.88
     baffling
    1.86
     astonished
    1.73
    Activations Density 0.051%

    No Known Activations