© 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. 66358
    Prev
    Next
    INDEX
    Explanations

    stored program, packets, radio frequency

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

    The neuron fires on technical‐domain keywords—specialized jargon naming system components, functions, or media (e.g. stored, program, screens, cameras, packet).

    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
    出来ない
    -1.04
     but
    -1.03
    проце
    -0.98
     by
    -0.95
     lelaki
    -0.92
    pum
    -0.88
     pulseras
    -0.88
    сайт
    -0.88
    (''),
    -0.88
     producto
    -0.85
    POSITIVE LOGITS
     instead
    1.83
     вместо
    1.38
     zamiast
    1.32
     istället
    1.27
    instead
    1.24
     rather
    1.23
    Instead
    1.16
     invece
    1.09
    而不是
    1.08
     yerine
    1.06
    Activations Density 0.123%

    No Known Activations