© 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. 118129
    Prev
    Next
    INDEX
    Explanations

    pizza or pizzeria

    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
     habituales
    -0.96
     habitually
    -0.87
     aquella
    -0.82
    の中では
    -0.78
     juries
    -0.77
    SECUR
    -0.77
    駆け
    -0.76
     Aussehen
    -0.76
     einzig
    -0.74
    おきます
    -0.74
    POSITIVE LOGITS
    🍕
    1.55
    iolo
    1.18
     Hut
    1.09
    zz
    1.03
    🍺
    1.01
    ⠀⠀
    0.97
     Dice
    0.92
     hut
    0.92
     febr
    0.92
    Night
    0.91
    Activations Density 0.012%

    No Known Activations