© 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. 130607
    Prev
    Next
    INDEX
    Explanations

    Continue reading

    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
    ził
    -0.87
    zionato
    -0.86
    Lorsque
    -0.85
    zić
    -0.83
    omaterial
    -0.83
    Cependant
    -0.79
     Improves
    -0.77
    ʮ
    -0.77
    ământ
    -0.77
     coö
    -0.76
    POSITIVE LOGITS
    fig
    0.78
    ḍ
    0.75
     indígena
    0.73
    [--
    0.73
     дом
    0.73
     -=
    0.73
     Mike
    0.71
     ctx
    0.69
     such
    0.69
     -
    0.69
    Activations Density 0.075%

    No Known Activations