© 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. 22-GEMMASCOPE-RES-131K
    4. 70549
    Prev
    Next
    INDEX
    Explanations

    prior to

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

    The neuron responds to punctuation marks that signal sentence boundaries—especially closing quotation marks and sentence-ending periods.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    varies
    -1.26
    presents
    -1.19
    humidité
    -1.10
     each
    -1.08
     Vorgang
    -1.03
     ihnen
    -1.03
     anunció
    -1.02
    ureusement
    -1.01
    ଵ
    -0.99
     masing
    -0.98
    POSITIVE LOGITS
     he
    1.38
     his
    1.25
     additionally
    1.08
     currently
    0.99
     uw
    0.98
    ètre
    0.93
     schu
    0.93
    dien
    0.91
     previously
    0.90
    CANCE
    0.90
    Activations Density 0.026%

    No Known Activations