© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43749
    Prev
    Next
    INDEX
    Explanations

    code punctuation and tangled

    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
    er
    -2.91
    しているので
    -2.67
    𓋼
    -2.66
    壟
    -2.66
    珢
    -2.59
     продукти
    -2.58
    悒
    -2.56
     незавер
    -2.53
    堉
    -2.53
    鶿
    -2.52
    POSITIVE LOGITS
     
    2.77
     "
    2.73
    は
    2.70
     ofere
    2.61
    </i>
    2.59
    はお
    2.53
    </h3>
    2.52
    -
    2.47
    THEY
    2.45
     ก็
    2.44
    Activations Density 0.003%

    No Known Activations