© 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. 11435
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    \
    -1.10
     или
    -1.08
    Those
    -1.05
    ،
    -1.05
    ō
    -1.04
     Those
    -1.03
    omento
    -1.02
    ,…
    -1.02
     Want
    -1.00
    zysty
    -1.00
    POSITIVE LOGITS
     récente
    1.16
     EXPERIMENTAL
    1.15
     francus
    1.13
    趋
    1.12
    入れて
    1.12
    más
    1.12
    以上に
    1.11
    㩒
    1.09
    チール
    1.09
    </h1>
    1.09
    Activations Density 0.186%

    No Known Activations