© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8222
    Prev
    Next
    INDEX
    Explanations

    one-time use or purchase

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

    The neuron strongly activates on the adverb “once,” i.e. one-time/first-time occurrences.

    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
     específicamente
    -1.30
     considerazione
    -1.14
     využí
    -1.12
     olvas
    -1.12
     gleichen
    -1.12
     of
    -1.10
     básicamente
    -1.05
    进一步
    -1.05
     ..."
    -1.04
     itd
    -1.04
    POSITIVE LOGITS
    Once
    1.41
     alebo
    1.40
    rvats
    1.35
    вні
    1.33
    وقال
    1.30
    𖡼
    1.27
    Meskipun
    1.25
    lorin
    1.25
    Sebelum
    1.23
    öhnen
    1.23
    Activations Density 0.050%

    No Known Activations