© 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. 101538
    Prev
    Next
    INDEX
    Explanations

    * enclosed text

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects text enclosed in asterisks (i.e. markdown-style emphasis/italic or bold markers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ly
    -1.70
    ねー
    -1.66
    you
    -1.48
    quirrels
    -1.47
    ной
    -1.46
    er
    -1.40
    le
    -1.40
    around
    -1.34
    ability
    -1.32
     kurzer
    -1.32
    POSITIVE LOGITS
    ());
    1.95
    <>();
    1.59
    ()).
    1.58
     їх
    1.58
     påvir
    1.55
    //!
    1.55
    )।
    1.54
    their
    1.51
    ”。
    1.51
    ”).
    1.48
    Activations Density 0.003%

    No Known Activations