© 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. 84334
    Prev
    Next
    INDEX
    Explanations

    discussing a question

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

    The neuron fires on tokens that start new sentences or message lines (i.e. initial, often capitalized, tokens at the beginning of a sentence or line).

    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
    ﻣ
    -1.27
    ﻷ
    -1.22
    ὕ
    -1.15
    ἵ
    -1.13
    ἴ
    -1.11
     menekan
    -1.09
     følge
    -1.08
    Zdrav
    -1.02
     '../../../../
    -1.01
    Recept
    -1.01
    POSITIVE LOGITS
     you
    1.92
     my
    1.80
     your
    1.80
     again
    1.25
     me
    1.16
     nuevamente
    1.16
     his
    1.13
     цвят
    1.13
    のですか
    1.13
     now
    1.10
    Activations Density 0.025%

    No Known Activations