© 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. 53981
    Prev
    Next
    INDEX
    Explanations

    code declaring variables

    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
    9
    -1.78
    4
    -1.70
    6
    -1.63
    8
    -1.63
    Five
    -1.63
    These
    -1.61
    Three
    -1.60
    What
    -1.58
    3
    -1.58
    2
    -1.53
    POSITIVE LOGITS
    тивов
    1.32
     but
    1.31
    commonly
    1.20
     QUESTIONS
    1.19
     domen
    1.17
    .“
    1.16
     “…
    1.16
    ={
    1.13
    {}
    1.13
    ffion
    1.13
    Activations Density 0.003%

    No Known Activations