© 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. 73800
    Prev
    Next
    INDEX
    Explanations

    names and roles

    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
    ాన
    -0.95
     beeintr
    -0.94
    ,—
    -0.88
     Эти
    -0.86
    ("");
    -0.80
     стрем
    -0.79
     Checked
    -0.78
    Anyways
    -0.77
    éez
    -0.77
    ulets
    -0.77
    POSITIVE LOGITS
     said
    1.06
    onomie
    0.98
    itemCount
    0.96
     mentioned
    0.94
    mány
    0.92
    ！！！！
    0.88
     של
    0.87
    名叫
    0.87
    ්
    0.86
     looking
    0.86
    Activations Density 0.002%

    No Known Activations