© 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. 654
    Prev
    Next
    INDEX
    Explanations

    physics models

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

    The neuron fires on numeric expressions and digits (including multi‐digit numbers and numeric tokens) in the text.

    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
     Universite
    -0.79
    CSRF
    -0.73
    只剩
    -0.71
    差距
    -0.70
     presumption
    -0.70
    adone
    -0.70
     پہ
    -0.69
    ending
    -0.69
    道歉
    -0.68
    submitButton
    -0.68
    POSITIVE LOGITS
     model
    1.63
     models
    1.55
     Model
    1.32
     modèle
    1.30
     Models
    1.27
    模型
    1.27
    model
    1.24
     модель
    1.24
    Models
    1.15
     modelu
    1.14
    Activations Density 0.115%

    No Known Activations