© 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. 63024
    Prev
    Next
    INDEX
    Explanations

    free software

    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
     hoang
    -0.70
     Bewegung
    -0.68
     nl
    -0.68
    esserung
    -0.68
    uken
    -0.68
     call
    -0.67
     الطب
    -0.67
     movement
    -0.66
    Guang
    -0.65
     provecho
    -0.65
    POSITIVE LOGITS
    events
    0.73
    넷
    0.70
    なお
    0.67
    プション
    0.66
    סי
    0.66
    rectangle
    0.65
    alahkan
    0.65
    cjon
    0.64
    fass
    0.63
    ***********
    0.63
    Activations Density 0.073%

    No Known Activations