© 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. 22-GEMMASCOPE-RES-131K
    7. 104582
    Prev
    Next
    INDEX
    Explanations

    any brand names

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

    The neuron fires on product model identifiers and technical spec tokens (e.g. brand-model codes and numbered product 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_22/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
    метра
    -1.20
     went
    -1.08
    ribue
    -1.03
    kilometer
    -1.02
    mathrm
    -1.02
     digna
    -1.02
    说到
    -1.02
    这是一
    -1.01
    勇者
    -1.01
    ске
    -1.00
    POSITIVE LOGITS
     your
    1.59
     любой
    1.26
     szüks
    1.22
     qualsiasi
    1.16
     qualquer
    1.16
     quaisquer
    1.13
    etap
    1.13
     existing
    1.13
     any
    1.07
     cualquier
    1.07
    Activations Density 0.072%

    No Known Activations