© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130880
    Prev
    Next
    INDEX
    Explanations

    responsibility, values, stories, accreditation, income, Cleveland

    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
     meis
    -1.68
    趿
    -1.57
     corriger
    -1.57
     substan
    -1.56
     tene
    -1.51
     adem
    -1.51
     cardin
    -1.50
     gela
    -1.47
     RAJ
    -1.47
     verba
    -1.47
    POSITIVE LOGITS
     HUGE
    1.70
     EVERY
    1.70
     ALL
    1.56
     longstanding
    1.49
     sizable
    1.48
     large
    1.46
     non
    1.44
     combines
    1.43
     for
    1.42
     low
    1.42
    Activations Density 0.015%

    No Known Activations