© 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. 22-GEMMASCOPE-RES-131K
    7. 79658
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    ляться
    -0.84
     Menor
    -0.81
    register
    -0.81
     lediglich
    -0.80
    шта
    -0.80
    》.
    -0.79
    ativeness
    -0.79
    好奇
    -0.79
    proceed
    -0.78
     ≤
    -0.78
    POSITIVE LOGITS
     there
    0.91
    asaran
    0.90
    türk
    0.88
    ᵕ
    0.84
    áncer
    0.82
     gruppo
    0.81
    žių
    0.81
     racconto
    0.81
     שיש
    0.81
    اقة
    0.81
    Activations Density 0.011%

    No Known Activations