© 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. 10-GEMMASCOPE-RES-131K
    7. 74209
    Prev
    Next
    INDEX
    Explanations

    we hope this

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

    The neuron fires on tokens that are parts of web addresses or URLs (e.g. “http,” “://,” domain names, “.org,” “/thread,” etc.).

    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
    𝗺
    -1.79
     शुर
    -1.73
     nepiecieš
    -1.60
    ῖ
    -1.59
    Gdzie
    -1.51
     daudz
    -1.50
     erfaren
    -1.48
    Zalety
    -1.45
     occidentalis
    -1.44
    Jakie
    -1.42
    POSITIVE LOGITS
     incluso
    2.05
    𓏸
    1.69
    ־ה
    1.68
    𓂂
    1.66
     everything
    1.65
     they
    1.64
     anything
    1.59
    וּ
    1.54
     anyone
    1.52
     cualquier
    1.50
    Activations Density 0.576%

    No Known Activations