© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66270
    Prev
    Next
    INDEX
    Explanations

    database and document context

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

    This neuron detects mentions of technical platform or API identifiers—particularly “Firebase,” “database,” and similar library or protocol names.

    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
    3
    -1.76
    >
    -1.69
    -1.57
    9
    -1.53
    ↵
    -1.47
    2
    -1.46
    -1.41
    ><
    -1.41
     erscheinen
    -1.40
     quitté
    -1.39
    POSITIVE LOGITS
     who
    1.80
     clínicas
    1.48
    をしました
    1.41
    aimeJ
    1.39
     verdaderas
    1.39
     ludzi
    1.38
     were
    1.34
    哢
    1.33
     ранее
    1.33
     únicamente
    1.33
    Activations Density 0.024%

    No Known Activations