© 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. 61292
    Prev
    Next
    INDEX
    Explanations

    channel followed by name or number

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

    This neuron detects mentions of TV channels (i.e. the word “Channel” followed by a number).

    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
    鰱
    -2.56
    が進
    -2.00
     télécommande
    -1.98
    鯷
    -1.98
     brightly
    -1.98
    に参加
    -1.93
     pensato
    -1.93
     creato
    -1.90
    </strong>
    -1.89
    をや
    -1.88
    POSITIVE LOGITS
     kutoka
    2.25
     от
    2.13
    béco
    2.08
     från
    2.06
    ve
    1.99
    ↵↵
    1.96
     แต่
    1.94
    quelize
    1.91
     pero
    1.89
    </td>
    1.85
    Activations Density 0.004%

    No Known Activations