© 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. 73649
    Prev
    Next
    INDEX
    Explanations

    Get Ready Set Code

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

    The neuron primarily activates on title-cased or fully capitalized tokens—i.e. proper names, acronyms, and stylized brand or album titles.

    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
     to
    -1.13
     gave
    -0.84
     seemed
    -0.84
     had
    -0.84
     took
    -0.83
    :​
    -0.82
    anyeol
    -0.81
    复杂的
    -0.81
     S
    -0.80
     schlecht
    -0.80
    POSITIVE LOGITS
    datable
    1.13
    Źródło
    1.10
    tych
    1.10
    Ź
    1.09
    久しぶり
    1.09
    VersionUID
    1.09
     БЕ
    1.09
    signable
    1.05
    ilever
    1.04
    Ö
    1.03
    Activations Density 0.070%

    No Known Activations