© 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. 10-GEMMASCOPE-RES-131K
    7. 57598
    Prev
    Next
    INDEX
    Explanations

    i2c, comments, programming context

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

    The neuron is detecting mentions of the I²C bus (i.e. “i2c” in code includes, device paths, or discussion of the I²C interface).

    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
    ’
    -2.44
     that
    -1.84
    henswürdigkeiten
    -1.74
    𓆝
    -1.64
    );
    -1.58
     albeit
    -1.55
    —“
    -1.53
     hieß
    -1.52
     αλλά
    -1.50
    tiembre
    -1.49
    POSITIVE LOGITS
    </em>
    1.67
     scanty
    1.60
     fácilmente
    1.55
     sorprend
    1.55
     potreb
    1.54
    </h3>
    1.52
     Très
    1.52
     automáticamente
    1.50
     fright
    1.48
     italien
    1.48
    Activations Density 0.010%

    No Known Activations