© 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. 34-GEMMASCOPE-RES-131K
    7. 116660
    Prev
    Next
    INDEX
    Explanations

    helping achieve a goal

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

    The neuron activates on four-digit numeric tokens (e.g., year or large-number strings).

    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
     soldadura
    -1.45
     that
    -1.37
    ⼭
    -1.35
     bicicletas
    -1.23
     aporte
    -1.23
     proteínas
    -1.21
     partículas
    -1.18
     fêtes
    -1.17
     hábit
    -1.13
     piscinas
    -1.13
    POSITIVE LOGITS
     to
    3.42
     in
    2.56
    ในการ
    1.49
     realizan
    1.05
     terão
    1.05
    而在
    1.03
    better
    1.02
     execução
    1.02
     במ
    1.00
     reconsider
    1.00
    Activations Density 0.034%

    No Known Activations