© 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. 98352
    Prev
    Next
    INDEX
    Explanations

    code and special characters

    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
    hộp
    -1.20
     chrétien
    -1.17
    dây
    -1.17
    虏
    -1.16
     expédié
    -1.16
    龔
    -1.16
    ʮ
    -1.16
    忤
    -1.16
    ſen
    -1.13
     vimos
    -1.13
    POSITIVE LOGITS
     olie
    1.14
    3
    1.13
     ijs
    1.06
    I
    1.05
     maja
    1.03
    ágenes
    1.02
    2
    1.02
    H
    1.02
     słon
    1.00
    0
    0.99
    Activations Density 0.126%

    No Known Activations