© 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. 22-GEMMASCOPE-RES-131K
    4. 446
    Prev
    Next
    INDEX
    Explanations

    location indices or coordinates

    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
     they
    -1.15
    ']?>
    -1.03
    volkswagen
    -1.03
    гмента
    -1.02
    nachweise
    -1.01
    skoda
    -1.00
    casque
    -0.96
    utella
    -0.96
     семь
    -0.96
     lựa
    -0.95
    POSITIVE LOGITS
     makhluk
    1.13
     яйцо
    1.07
    iress
    1.07
    odora
    1.00
    rises
    0.97
    madeus
    0.96
     cristianismo
    0.95
    nachron
    0.95
     perbaikan
    0.94
     Diener
    0.94
    Activations Density 0.022%

    No Known Activations