© 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. 34-GEMMASCOPE-RES-131K
    7. 7279
    Prev
    Next
    INDEX
    Explanations

    lists with numbers or dates

    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
    ugia
    -0.76
     粉
    -0.72
     sintió
    -0.71
     traveler
    -0.69
    meleon
    -0.69
    ladiator
    -0.69
     jedynie
    -0.68
     chloroform
    -0.67
     Hmmm
    -0.67
     fédéral
    -0.66
    POSITIVE LOGITS
     STREAM
    0.96
    갚
    0.82
    Srv
    0.82
    AudioManager
    0.79
    Begriffsklä
    0.79
     ducks
    0.78
    omencl
    0.76
     streams
    0.75
    keycode
    0.75
    步骤
    0.74
    Activations Density 0.012%

    No Known Activations