© 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. 28432
    Prev
    Next
    INDEX
    Explanations

    name origin explanation

    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
     bastante
    -0.87
    cinoma
    -0.86
    TAINMENT
    -0.84
    Administ
    -0.84
     invisible
    -0.83
     ตา
    -0.80
    lugin
    -0.79
    toMap
    -0.78
     UIButton
    -0.78
     information
    -0.77
    POSITIVE LOGITS
     its
    1.28
     because
    1.27
     نسبة
    1.05
    because
    0.91
     when
    0.88
    caja
    0.88
    τρο
    0.88
    ヨン
    0.88
     omdat
    0.85
    因為
    0.85
    Activations Density 0.099%

    No Known Activations