© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85911
    Prev
    Next
    INDEX
    Explanations

    punctuation and abbreviations

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

    This neuron responds to non‐letter formatting characters—whitespace, punctuation, and other separator symbols.

    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
    chó
    -1.52
    erráneo
    -1.49
     })}
    -1.48
    pó
    -1.42
    aş
    -1.42
     betrek
    -1.41
    mink
    -1.40
     paramInt
    -1.39
    mtliche
    -1.36
     MessageBoxIcon
    -1.35
    POSITIVE LOGITS
    s
    1.73
    y
    1.63
    N
    1.55
    in
    1.54
    if
    1.54
     Erfüllung
    1.52
    j
    1.49
    by
    1.48
     Our
    1.46
     About
    1.46
    Activations Density 0.014%

    No Known Activations