© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14465
    Prev
    Next
    INDEX
    Explanations

    New Delhi

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

    The neuron strongly activates on numeric tokens and URL/domain fragments (e.g. digits, years, “www,” domain names, and hyphenated address parts).

    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
     annihil
    -0.99
     Kini
    -0.96
     ابتدا
    -0.93
     Surve
    -0.93
    вање
    -0.93
    INSTAGRAM
    -0.91
    followed
    -0.90
    ajara
    -0.90
     Hymn
    -0.90
     daarna
    -0.88
    POSITIVE LOGITS
     during
    1.16
     lors
    0.86
     vás
    0.86
     there
    0.86
    𝚊
    0.85
    kram
    0.84
     podczas
    0.81
    живать
    0.81
     بگذار
    0.80
     comiendo
    0.79
    Activations Density 0.046%

    No Known Activations