© 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. 22-GEMMASCOPE-RES-131K
    7. 95510
    Prev
    Next
    INDEX
    Explanations

    introductions, details, or structural markers

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

    The neuron fires most strongly on tokens that mark structural boundaries—e.g. end-of-sentence punctuation, list or section numbers, and other layout markers.

    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
    ആ
    -1.18
    ഇ
    -1.18
    આ
    -1.13
    అ
    -1.11
     Templo
    -1.03
    sejarah
    -1.03
     apartament
    -1.02
    ֶר
    -1.01
    അ
    -1.01
     appartement
    -0.99
    POSITIVE LOGITS
     his
    1.17
    ことも
    1.13
    ところに
    1.12
     ακόμα
    1.09
     farklı
    1.05
    色んな
    1.04
    はもう
    1.03
     almeno
    1.02
    為に
    1.01
     vuol
    0.99
    Activations Density 0.000%

    No Known Activations