© 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. 19698
    Prev
    Next
    INDEX
    Explanations

    ICA, DNS, Agri, LDS, OSM

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

    The neuron fires on short technical or organizational abbreviations and acronyms (e.g. ICA, DNS, OSM, LDS, “Agri,” “Aad”), i.e. tokens that look like initialisms.

    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
    轳
    -2.94
    🗹
    -2.84
    などが
    -2.72
     "
    -2.55
    𝅥
    -2.50
     但
    -2.44
     sieben
    -2.41
     —
    -2.41
    racene
    -2.41
    不过是
    -2.39
    POSITIVE LOGITS
    </strong>
    3.00
    戗
    2.88
     itſelf
    2.70
    赑
    2.63
    r
    2.53
    
    2.50
     内衣
    2.48
     credere
    2.44
    '>";
    2.44
    缦
    2.42
    Activations Density 0.009%

    No Known Activations