© 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. 36029
    Prev
    Next
    INDEX
    Explanations

    having something to

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

    The neuron fires on key content words—especially nouns and main verbs—in expository or technical passages, effectively highlighting the topic‐bearing terms of a sentence.

    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
    allerie
    -0.99
     через
    -0.94
     любы
    -0.92
     entornos
    -0.92
     elseif
    -0.88
     parfois
    -0.88
    的其他
    -0.87
     evidentemente
    -0.87
     acaso
    -0.85
    会话
    -0.85
    POSITIVE LOGITS
     handy
    1.26
     access
    1.20
     someone
    1.08
     for
    1.08
     reliable
    1.07
    cityId
    1.07
     convenient
    1.02
     having
    1.02
    良好的
    1.00
     excuse
    0.97
    Activations Density 0.037%

    No Known Activations