© 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. 48205
    Prev
    Next
    INDEX
    Explanations

    code modules and functions

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

    The neuron fires on tokens containing underscores—i.e. parts of file names, include paths, or identifiers that use “_.”

    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
    𓆸
    -1.77
    輒
    -1.74
     Anschließend
    -1.70
     Nachdem
    -1.61
     Danach
    -1.59
    ètre
    -1.58
     завжди
    -1.57
    齶
    -1.48
    餬
    -1.48
     “
    -1.45
    POSITIVE LOGITS
     we
    2.31
     they
    1.73
     about
    1.67
     a
    1.55
    </em>
    1.52
    In
    1.49
     немного
    1.41
     menurut
    1.40
    最重要的
    1.35
    </u>
    1.33
    Activations Density 0.066%

    No Known Activations