© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12806
    Prev
    Next
    INDEX
    Explanations

    sequence completion

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

    The neuron fires on the main content words—salient topical nouns, adjectives, and verbs that carry the core meaning of each 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_10/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
    鰾
    -1.74
    dată
    -1.59
    䨻
    -1.55
    銥
    -1.54
    媵
    -1.52
    镬
    -1.50
    鴆
    -1.49
     deſt
    -1.49
     GOtt
    -1.48
     手順
    -1.48
    POSITIVE LOGITS
    )
    2.20
     will
    2.16
     on
    2.14
     at
    1.94
     is
    1.82
    }
    1.80
     now
    1.70
    ↵
    1.69
      
    1.68
    even
    1.68
    Activations Density 0.024%

    No Known Activations