© 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. 10-GEMMASCOPE-RES-131K
    4. 41501
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

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

    The neuron fires strongly on standalone topic words or headings—i.e. the key nouns or labels that typically appear as section titles or main-topic markers in a 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_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
    Additionally
    -1.63
     моего
    -1.47
    荭
    -1.40
    忘记
    -1.38
    CHREIB
    -1.38
     hadden
    -1.34
    Therefore
    -1.31
     soooo
    -1.30
     gewisse
    -1.29
     ſever
    -1.27
    POSITIVE LOGITS
     will
    2.00
     all
    1.70
     may
    1.59
     we
    1.59
    !"
    1.55
     both
    1.52
     only
    1.52
     are
    1.51
     might
    1.48
     then
    1.41
    Activations Density 0.001%

    No Known Activations