© 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. 22-GEMMASCOPE-RES-131K
    7. 72504
    Prev
    Next
    INDEX
    Explanations

    claim, summer heat, bass

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

    The neuron fires on standalone numeric tokens and all‐caps words—i.e. table or metadata entries like race numbers, prices, or section headings.

    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
     for
    -1.22
    acı
    -1.21
     before
    -1.15
    ræ
    -1.13
     kronor
    -1.11
    economic
    -1.10
     already
    -1.10
    funk
    -1.09
     changes
    -1.08
     continuously
    -1.08
    POSITIVE LOGITS
     declaró
    1.42
     другим
    1.41
    んでる
    1.34
     Кубка
    1.34
     refirió
    1.26
    inverno
    1.23
     chargés
    1.22
     indicó
    1.19
     evtl
    1.19
     lahko
    1.16
    Activations Density 0.000%

    No Known Activations