© 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. 22-GEMMASCOPE-RES-131K
    7. 36213
    Prev
    Next
    INDEX
    Explanations

    controller or requests

    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
     Karakter
    -1.13
     Ilustra
    -1.09
     kamb
    -1.09
     wüns
    -1.06
     bringe
    -1.05
     possesso
    -1.03
     decidido
    -1.02
    selben
    -1.02
     potrebbero
    -1.02
     erhi
    -1.01
    POSITIVE LOGITS
    鋅
    1.29
     Just
    1.12
     neue
    1.08
    ны
    1.05
     Data
    1.05
     Hand
    1.00
     {}));
    1.00
     geomé
    0.99
    VIATIONS
    0.97
     Only
    0.96
    Activations Density 0.002%

    No Known Activations