© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7238
    Prev
    Next
    INDEX
    Explanations

    code structure and lists

    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
    ABBRE
    -0.85
    ⍝
    -0.82
     seleccionado
    -0.81
     luta
    -0.80
     testing
    -0.78
     Kennedy
    -0.76
    Kik
    -0.76
     Send
    -0.76
     Stocks
    -0.75
     során
    -0.75
    POSITIVE LOGITS
     NSMutable
    0.81
    undefined
    0.74
     phenomena
    0.73
     degrés
    0.72
     wahrscheinlich
    0.69
    stmt
    0.69
    vii
    0.68
    榔
    0.68
     Straf
    0.68
    comes
    0.68
    Activations Density 0.001%

    No Known Activations