© 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. 34-GEMMASCOPE-RES-131K
    7. 50316
    Prev
    Next
    INDEX
    Explanations

    films starting with Fray or starring names

    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
    itou
    -0.86
    cijas
    -0.79
     brady
    -0.77
     fått
    -0.77
    僖
    -0.76
     minions
    -0.75
    AVEN
    -0.74
     dispers
    -0.73
     把
    -0.73
    bernate
    -0.72
    POSITIVE LOGITS
     réalis
    0.87
     FR
    0.82
    Fic
    0.81
     Fr
    0.79
     Friend
    0.73
     Fried
    0.72
    FR
    0.72
     guten
    0.71
    šia
    0.71
    呼ば
    0.71
    Activations Density 0.053%

    No Known Activations