© 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. 107396
    Prev
    Next
    INDEX
    Explanations

    look for

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

    The neuron strongly responds to punctuation tokens—especially sentence-ending symbols like periods and colons.

    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
     consultato
    -1.03
     IndexPath
    -0.94
    =$?
    -0.93
     FÜR
    -0.88
    DriverManager
    -0.87
    AtIndexPath
    -0.87
    🕙
    -0.86
    ᐕ
    -0.86
     РС
    -0.85
    咲
    -0.85
    POSITIVE LOGITS
     look
    2.95
    Look
    2.56
     Look
    2.30
    look
    2.22
     choose
    1.97
     check
    1.82
    LOOK
    1.72
     seek
    1.70
     search
    1.61
     LOOK
    1.59
    Activations Density 0.027%

    No Known Activations