© 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. 93171
    Prev
    Next
    INDEX
    Explanations

    implementation details or descriptions

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

    The neuron is primarily triggered by colon punctuation (":"), especially in code comments or documentation, marking parameter labels and section headings.

    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
     見える
    -1.16
    ENOMEM
    -1.15
    Æ
    -1.02
    𝗧
    -1.02
     commons
    -0.98
     ae
    -0.98
     ______
    -0.98
    emptyset
    -0.97
     gibts
    -0.97
     appellant
    -0.96
    POSITIVE LOGITS
     from
    1.56
     in
    1.53
     に関する
    1.36
     for
    1.31
     since
    1.23
     weren
    1.23
    Langkah
    1.09
     so
    1.09
     purposefully
    1.08
     purposely
    1.07
    Activations Density 0.032%

    No Known Activations