© 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. 12425
    Prev
    Next
    INDEX
    Explanations

    conditional programming language statements

    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
    kömm
    -1.00
    مزید
    -0.98
    même
    -0.86
     lavable
    -0.86
     abstracto
    -0.84
     ögon
    -0.83
    Thiết
    -0.83
    ushchev
    -0.83
    ración
    -0.82
    tilles
    -0.82
    POSITIVE LOGITS
     if
    0.85
    If
    0.80
     If
    0.80
     skóry
    0.80
     зима
    0.78
    ためには
    0.77
     Daerah
    0.74
     muốn
    0.73
     wanted
    0.73
     genauer
    0.72
    Activations Density 0.005%

    No Known Activations