© 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. 84149
    Prev
    Next
    INDEX
    Explanations

    report finds. climate

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

    The neuron is detecting punctuation characters—particularly sentence-ending periods and apostrophes.

    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
     you
    -1.82
    ὸν
    -1.38
    ὴν
    -1.27
     I
    -1.26
     microondas
    -1.23
     bobina
    -1.22
     luminoso
    -1.20
     alza
    -1.18
     מים
    -1.16
     viſ
    -1.16
    POSITIVE LOGITS
     according
    1.34
     thus
    1.29
    ύ
    1.27
     recent
    1.27
     such
    1.22
    Such
    1.21
     beispielsweise
    1.19
    ִּ
    1.19
     many
    1.18
     since
    1.18
    Activations Density 0.041%

    No Known Activations