© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38541
    Prev
    Next
    INDEX
    Explanations

    end of clause or sentence

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

    The neuron responds to punctuation tokens—especially sentence-ending marks like periods and exclamation points.

    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
     остается
    -1.48
    たとえば
    -1.36
     einschließlich
    -1.30
    ർ
    -1.23
     еще
    -1.20
     wenigstens
    -1.20
     since
    -1.20
     organized
    -1.20
     farther
    -1.18
     colorful
    -1.15
    POSITIVE LOGITS
    Whilst
    2.58
     whilst
    2.53
     Whilst
    2.30
     it
    1.35
    ですので
    1.30
    Util
    1.26
     whist
    1.16
    Έ
    1.16
     допусти
    1.15
     aswell
    1.14
    Activations Density 0.102%

    No Known Activations