© 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. 34-GEMMASCOPE-RES-131K
    7. 94143
    Prev
    Next
    INDEX
    Explanations

    Franco Corelli, Q:, According to

    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_34/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
     سین
    -0.85
    设
    -0.77
     background
    -0.76
    栏
    -0.73
     assume
    -0.71
    Afghan
    -0.71
    PDOException
    -0.70
     STUDENT
    -0.70
    ETHYL
    -0.69
    centerTitle
    -0.69
    POSITIVE LOGITS
     Montpellier
    0.89
    滋賀
    0.81
     虎
    0.74
     Umbra
    0.69
    чам
    0.69
    entsch
    0.69
     등록
    0.69
    祉
    0.68
     weary
    0.68
    isReady
    0.68
    Activations Density 0.016%

    No Known Activations