© 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. 10-GEMMASCOPE-RES-131K
    7. 9244
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

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

    The neuron strongly activates on period characters—whether single dots, runs of dots (ellipses), or decimal‐point fragments.

    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
    ᯅ
    -1.60
     Água
    -1.56
    nargs
    -1.53
    />";
    -1.52
    Ẳ
    -1.45
    ſſion
    -1.42
     refor
    -1.41
     vies
    -1.39
    尧
    -1.38
     pernic
    -1.37
    POSITIVE LOGITS
    9
    2.23
    5
    1.96
    2
    1.96
    8
    1.86
    n
    1.82
    3
    1.80
    4
    1.79
    ↵
    1.76
     these
    1.67
    1
    1.66
    Activations Density 0.007%

    No Known Activations