© 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. 1734
    Prev
    Next
    INDEX
    Explanations

    seeking clarification or explanation

    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
     connues
    -1.34
    简约
    -1.27
    熥
    -1.25
    Yok
    -1.23
    ulemon
    -1.20
     apparaissent
    -1.20
     bambú
    -1.20
    唖
    -1.16
     \
    -1.14
    es
    -1.13
    POSITIVE LOGITS
    For
    1.37
     by
    1.31
     with
    1.30
     κάπο
    1.30
    Some
    1.29
    Ár
    1.27
     Untuk
    1.27
     under
    1.26
     mengenakan
    1.26
    Because
    1.24
    Activations Density 0.104%

    No Known Activations