© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27888
    Prev
    Next
    INDEX
    Explanations

    both words

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

    The neuron responds to standalone numeric tokens (e.g. years, volume/page numbers) in the text.

    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
     all
    -2.23
     semua
    -1.33
     All
    -1.22
    どれ
    -1.21
    ?,?,
    -1.20
     todas
    -1.18
    All
    -1.16
     tất
    -1.13
     drei
    -1.12
    どれも
    -1.11
    POSITIVE LOGITS
     both
    2.52
     beide
    2.45
     Beide
    2.38
     beiden
    2.28
     ambos
    2.27
    Both
    2.23
     begge
    2.22
     entrambi
    2.19
    Ambos
    2.16
     दोनों
    2.14
    Activations Density 0.007%

    No Known Activations