© 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. 93949
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by a word

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

    The neuron fires on literal constants—numbers or quoted string values appearing in the code.

    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
     in
    -1.48
    個室
    -1.20
    饗
    -1.19
     to
    -1.17
    儀式
    -1.16
     but
    -1.15
     (
    -1.13
     amidst
    -1.11
     odpově
    -1.09
    させていただきました
    -1.08
    POSITIVE LOGITS
     qualsiasi
    1.39
    為に
    1.30
    ㅛ
    1.30
     cualquiera
    1.27
     ,.
    1.27
     .........
    1.24
    ところです
    1.20
     .............
    1.20
     ','
    1.17
     betere
    1.15
    Activations Density 0.055%

    No Known Activations