© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79610
    Prev
    Next
    INDEX
    Explanations

    numbers and slight differences

    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
    luca
    -0.81
    遠
    -0.78
     bajo
    -0.78
     jauh
    -0.77
    reditation
    -0.77
     dál
    -0.76
    uesa
    -0.75
    ۷
    -0.75
    远
    -0.74
     deste
    -0.73
    POSITIVE LOGITS
     slightly
    1.13
     Slightly
    0.94
    slightly
    0.88
     marginally
    0.88
     slight
    0.82
     dernière
    0.81
    ちょっとした
    0.81
     attravers
    0.81
     légèrement
    0.80
     similar
    0.80
    Activations Density 0.016%

    No Known Activations