© 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. 22-GEMMASCOPE-RES-131K
    7. 104609
    Prev
    Next
    INDEX
    Explanations

    Contact Information

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

    This neuron detects question contexts, especially the question‐mark punctuation in Q&A-style text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kategori
    -1.41
     refroidissement
    -1.37
    مجموع
    -1.32
     pantalon
    -1.30
     Ekonomi
    -1.29
     無地
    -1.28
    }}_
    -1.28
     ekonomi
    -1.27
     abbildung
    -1.24
    #
    -1.23
    POSITIVE LOGITS
    íguez
    1.59
     they
    1.34
     who
    1.32
     could
    1.31
     their
    1.31
     braço
    1.30
     there
    1.29
     that
    1.29
     deportivas
    1.29
     since
    1.28
    Activations Density 0.035%

    No Known Activations