© 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. 54258
    Prev
    Next
    INDEX
    Explanations

    name assignment

    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
    软件特色
    -1.06
     Lune
    -1.06
    hanced
    -1.04
     Juin
    -1.03
     twarzy
    -0.98
     itinéraires
    -0.97
     itinerario
    -0.96
    是怎么回事
    -0.96
     fungerar
    -0.96
     Île
    -0.95
    POSITIVE LOGITS
    طلحات
    1.02
    іб
    0.98
    lrrr
    0.98
    Jeśli
    0.96
     Ministers
    0.96
     cucchiai
    0.96
     Downtown
    0.95
     Kräuter
    0.93
     упаковке
    0.93
     name
    0.93
    Activations Density 0.002%

    No Known Activations