© 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. 89820
    Prev
    Next
    INDEX
    Explanations

    code comments for files

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

    This neuron fires on numeric date and version strings (e.g. years, month/day/year sequences, build numbers) found in code comments.

    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
     there
    -1.24
    ynie
    -0.92
    vané
    -0.91
    <tbody>
    -0.91
     jugó
    -0.91
    ͈
    -0.90
    んですよね
    -0.90
     هناك
    -0.88
    éte
    -0.88
    +{
    -0.85
    POSITIVE LOGITS
    ]$.
    0.77
     Bunun
    0.77
     wym
    0.75
    believe
    0.74
    貼り
    0.70
    student
    0.69
     student
    0.69
    reason
    0.69
    lingual
    0.68
     harika
    0.68
    Activations Density 0.015%

    No Known Activations