© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26456
    Prev
    Next
    INDEX
    Explanations

    series and book titles

    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_22/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
    scraper
    -0.91
     erwähnten
    -0.91
     Gelegenheit
    -0.89
     could
    -0.85
    hiya
    -0.84
     antidesliz
    -0.81
     lavable
    -0.80
     equipment
    -0.80
     recogida
    -0.79
    に行ってきました
    -0.78
    POSITIVE LOGITS
    シリーズ
    1.13
     series
    1.05
     seiner
    0.98
     Series
    0.98
     angusti
    0.96
    龛
    0.93
     Série
    0.91
     Ato
    0.90
     actes
    0.90
    lorus
    0.88
    Activations Density 0.021%

    No Known Activations