© 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. 118237
    Prev
    Next
    INDEX
    Explanations

    can take

    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
     erschien
    -0.80
    RICULUM
    -0.78
    pei
    -0.77
    osoma
    -0.75
    ッケージ
    -0.73
    teiro
    -0.72
    jshint
    -0.72
     igenom
    -0.71
    皎
    -0.71
    wpdb
    -0.70
    POSITIVE LOGITS
     take
    2.94
    采取
    2.77
    taking
    2.66
     taking
    2.64
     took
    2.50
    take
    2.42
     prendre
    2.38
    Taking
    2.38
     tomar
    2.33
     takes
    2.27
    Activations Density 0.052%

    No Known Activations