© 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. 10-GEMMASCOPE-RES-131K
    7. 87082
    Prev
    Next
    INDEX
    Explanations

    girl camera

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

    The neuron fires on isolated content-bearing tokens—especially standalone nouns or other key topic words.

    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
    a
    -3.30
    ा
    -2.80
    1
    -2.77
    ة
    -2.75
    What
    -2.75
    the
    -2.50
    </h1>
    -2.50
    Eight
    -2.44
    Who
    -2.38
    냇
    -2.33
    POSITIVE LOGITS
     are
    2.56
     máme
    2.30
    的特点
    2.22
     contém
    2.20
    的产品
    2.20
    
    2.16
     daring
    2.09
    ⸂
    2.08
    笮
    2.08
    中最
    2.08
    Activations Density 0.000%

    No Known Activations