© 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. 59144
    Prev
    Next
    INDEX
    Explanations

    web addresses and code

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

    This neuron fires on technical and code‐like tokens—especially parts of URLs, file paths, domain names, script or library names, and numeric or version identifiers.

    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
     скла
    -0.93
     manufact
    -0.77
    fake
    -0.75
     drewni
    -0.73
    秘书
    -0.73
    一開始
    -0.73
     Atm
    -0.71
     judicious
    -0.70
     pulmonar
    -0.70
    
    -0.70
    POSITIVE LOGITS
     barking
    0.86
    اً
    0.85
    umented
    0.82
     Commerce
    0.82
     sighs
    0.79
    rahat
    0.77
    >().
    0.76
     Webb
    0.75
    ًا
    0.72
     Meier
    0.72
    Activations Density 0.030%

    No Known Activations