© 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. 59161
    Prev
    Next
    INDEX
    Explanations

    sentences that end with punctuation

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

    This neuron tracks how far into a text segment we are, firing more strongly on tokens that appear later (e.g. near the end of a paragraph or document).

    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
     вами
    -1.20
     musst
    -1.17
    ৄ
    -1.12
     bija
    -1.07
     you
    -1.02
     gouverneur
    -1.02
     NEEDS
    -1.02
    needs
    -1.02
    йтесь
    -1.01
    olution
    -1.00
    POSITIVE LOGITS
     should
    2.42
     would
    2.22
     what
    1.99
     Should
    1.97
     my
    1.91
     is
    1.85
     What
    1.80
     how
    1.80
     Would
    1.78
     does
    1.77
    Activations Density 0.669%

    No Known Activations