© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33149
    Prev
    Next
    INDEX
    Explanations

    hash or pound sign in text

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

    The neuron fires on mentions of URL “hash” fragments—that is, parts of links or code using “#…” and the term “hash.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    itale
    -0.85
    vertret
    -0.82
     母
    -0.80
    Pap
    -0.75
    żs
    -0.74
     Coen
    -0.74
     Coolidge
    -0.73
    imli
    -0.73
     pembeli
    -0.72
    猜
    -0.72
    POSITIVE LOGITS
     "#"
    2.31
     '#'
    2.28
    ("#
    2.14
    #
    1.99
    ('#
    1.96
     hash
    1.95
     #
    1.95
     "#
    1.88
     \#
    1.80
    ='#
    1.75
    Activations Density 0.054%

    No Known Activations