© 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. 20567
    Prev
    Next
    INDEX
    Explanations

    `com.` identifiers

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

    The neuron fires on the “com.” segments of reverse-domain identifiers (e.g. package or bundle IDs).

    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
    </em>
    -1.63
    蛲
    -1.59
     envía
    -1.52
    already
    -1.48
     prevé
    -1.38
     aproxim
    -1.38
    ▪
    -1.38
     trois
    -1.36
    preneurs
    -1.36
     mimicking
    -1.35
    POSITIVE LOGITS
     only
    1.97
     from
    1.66
     including
    1.55
     až
    1.43
     at
    1.43
     which
    1.41
    ꒷
    1.40
     initially
    1.38
     having
    1.37
    Despite
    1.36
    Activations Density 0.017%

    No Known Activations