© 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. 34-GEMMASCOPE-RES-131K
    7. 82376
    Prev
    Next
    INDEX
    Explanations

    state of being or action

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

    The neuron preferentially activates on semantically important content words (not grammatical function words), such as key nouns and verbs that carry the main technical or topical meaning of a passage.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    為に
    -2.55
    さぁ
    -2.33
    の方に
    -2.28
    久し
    -2.27
    ほら
    -2.23
    を探す
    -2.20
    あぁ
    -2.19
    えっ
    -2.13
    感じが
    -2.13
    ところに
    -2.11
    POSITIVE LOGITS
    を
    2.03
    と
    1.98
    が
    1.95
    <bos>
    1.87
     Grüßen
    1.77
    や
    1.76
    參考文獻
    1.76
    そして
    1.65
    そのため
    1.63
    も
    1.62
    Activations Density 1.238%

    No Known Activations