© 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. 124001
    Prev
    Next
    INDEX
    Explanations

    Oculus and ocular

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

    terms related to vision technology and optical research, particularly mentioning "ocular" and "Oculus" products.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on any token containing the letter bigram “oc” (e.g. pico, second, Oculus, ocular, PEPICO).

    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
     generando
    -2.59
    écrire
    -2.34
     cambiando
    -2.30
     creando
    -2.13
     Instead
    -2.05
     spans
    -1.89
     Teléfono
    -1.89
    apprendre
    -1.88
    by
    -1.88
     However
    -1.88
    POSITIVE LOGITS
    ’，
    2.67
    嵛
    2.61
     mein
    2.47
     meine
    2.34
    皤
    2.14
    法國
    2.14
     meu
    2.13
    噲
    2.08
    ࿙
    2.06
    𖡼
    2.06
    Activations Density 0.008%

    No Known Activations