© 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. 22-GEMMASCOPE-RES-131K
    7. 71730
    Prev
    Next
    INDEX
    Explanations

    commas and specific words

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

    The neuron fires on punctuation characters (commas, question marks, and similar delimiters).

    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
     his
    -1.20
     their
    -1.19
    ⿱
    -1.05
     уже
    -1.04
    尛
    -1.02
    ________,
    -1.00
     already
    -0.98
     Letra
    -0.97
     ketidak
    -0.96
     Drž
    -0.96
    POSITIVE LOGITS
    Yes
    1.32
    Approximately
    1.20
    Currently
    1.07
    の人は
    1.06
    9
    1.05
     yes
    1.05
    w
    1.04
    Y
    1.04
    gs
    1.02
    確實
    1.02
    Activations Density 0.001%

    No Known Activations