© 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. 104318
    Prev
    Next
    INDEX
    Explanations

    how something works

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

    The neuron strongly activates on the word “how,” flagging constructions that introduce explanations, instructions, or questions.

    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
    l
    -2.19
     This
    -2.16
     Also
    -1.79
     recounted
    -1.75
     It
    -1.75
    ate
    -1.70
     attempt
    -1.70
     Another
    -1.68
     ialah
    -1.67
    "
    -1.67
    POSITIVE LOGITS
     we
    2.22
    荭
    1.91
     \
    1.91
    抔
    1.88
     our
    1.76
    libatkan
    1.75
     this
    1.73
     вашей
    1.73
     their
    1.71
     they
    1.69
    Activations Density 0.059%

    No Known Activations