© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3048
    Prev
    Next
    INDEX
    Explanations

    URL encoding and decoding

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

    The neuron fires on numeric literals (sequences of digits) 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
     Invo
    -0.81
    ഉ
    -0.76
    ändig
    -0.69
    nod
    -0.68
    jahre
    -0.68
    Sheets
    -0.67
    тай
    -0.67
     thickness
    -0.65
    ärke
    -0.64
    chmal
    -0.63
    POSITIVE LOGITS
     Besuch
    0.70
    gawa
    0.69
    衣裙
    0.69
     Residence
    0.69
     Destroy
    0.68
    =-
    0.68
     Problem
    0.67
    ギ
    0.67
     сла
    0.66
     Boxer
    0.66
    Activations Density 0.075%

    No Known Activations