© 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. 10-GEMMASCOPE-RES-131K
    7. 75312
    Prev
    Next
    INDEX
    Explanations

    Spanish and Portuguese beginnings

    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
     risiko
    -2.72
     lej
    -2.72
     maksi
    -2.72
    ープン
    -2.67
    𖥦
    -2.64
    U
    -2.59
     eier
    -2.53
     bilder
    -2.50
     hennes
    -2.47
     venner
    -2.47
    POSITIVE LOGITS
     he
    3.06
     of
    2.83
    ].
    2.52
     anschließend
    2.50
    </strong>
    2.47
     diversos
    2.44
     intric
    2.33
     outras
    2.30
    dreamstime
    2.28
    <em>
    2.16
    Activations Density 0.003%

    No Known Activations