© 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. 10-GEMMASCOPE-RES-131K
    4. 75037
    Prev
    Next
    INDEX
    Explanations

    one + specific noun

    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_10/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
    乄
    -1.81
     It
    -1.79
     لأن
    -1.71
     scars
    -1.70
     ワイン
    -1.65
     REALLY
    -1.64
    쨩
    -1.63
    是大
    -1.55
    谁
    -1.55
     wichtigsten
    -1.52
    POSITIVE LOGITS
     two
    1.95
    !’
    1.93
     three
    1.84
     “
    1.76
     gave
    1.73
     would
    1.65
     six
    1.61
     IMPLICATIONS
    1.60
     five
    1.60
     four
    1.60
    Activations Density 0.053%

    No Known Activations