© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    custard

    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
     pepperoni
    -0.82
    GETHER
    -0.82
     Fries
    -0.81
    zaron
    -0.81
     EVALUATION
    -0.79
    oose
    -0.79
    Fries
    -0.77
    ústria
    -0.77
    rove
    -0.76
     dầu
    -0.75
    POSITIVE LOGITS
     custard
    1.84
     cust
    1.35
     Cust
    1.30
    cust
    1.22
    🍮
    1.16
    Cust
    1.08
     eggs
    1.07
     egg
    1.06
    蛋
    0.95
    CUST
    0.90
    Activations Density 0.012%

    No Known Activations