© 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. 98458
    Prev
    Next
    INDEX
    Explanations

    increasing or decreasing trends

    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
    突然
    -1.09
    ském
    -1.05
     レストラン
    -1.05
    ################
    -1.04
    出版社
    -1.02
    Erstellt
    -1.01
    Aktualisiert
    -1.01
    gado
    -1.01
    Với
    -1.01
    ｋ
    -0.99
    POSITIVE LOGITS
     in
    1.45
    何より
    1.20
     towards
    1.18
    囁
    1.13
    uteurs
    1.13
    などなど
    1.10
     year
    1.10
     since
    1.09
     României
    1.09
    百分之
    1.07
    Activations Density 0.045%

    No Known Activations