© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32059
    Prev
    Next
    INDEX
    Explanations

    frozen food items

    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
     cottura
    -0.87
     représentent
    -0.86
     combattre
    -0.85
    ENSUS
    -0.83
    dsk
    -0.81
     mangiare
    -0.80
     wichtigsten
    -0.79
    matrices
    -0.76
     belangrijk
    -0.75
     prenotazione
    -0.75
    POSITIVE LOGITS
     yogurt
    0.94
     Solid
    0.88
     foods
    0.86
    ン
    0.86
     peas
    0.85
    set
    0.85
    Solid
    0.82
     Dai
    0.82
    现代
    0.81
     solid
    0.80
    Activations Density 0.020%

    No Known Activations