© 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. 36691
    Prev
    Next
    INDEX
    Explanations

    modelcode preceding model names

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

    The neuron detects ORM-style model relationship declarations (e.g. hasMany(…) or belongsTo(…) with class names).

    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
    PriorityQueue
    -0.91
    补充
    -0.90
     indústria
    -0.90
    劻
    -0.90
    儈
    -0.90
    леты
    -0.90
    oners
    -0.89
    ⤥
    -0.89
    鮠
    -0.88
    SHIPPING
    -0.86
    POSITIVE LOGITS
     empiezan
    1.07
     désormais
    1.07
     other
    1.05
     of
    1.05
    𝚞
    1.02
     hånd
    1.00
     теперь
    0.98
    んでいた
    0.97
     suelen
    0.95
     spise
    0.95
    Activations Density 0.006%

    No Known Activations