© 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. 34787
    Prev
    Next
    INDEX
    Explanations

    with or prior to

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

    The main thing this neuron does is detect numeric tokens (digits and 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
     dvs
    -1.23
     these
    -1.20
     when
    -1.19
     on
    -1.16
     by
    -1.13
     before
    -1.13
     this
    -1.11
     transporta
    -1.11
     identifica
    -1.09
     kunjungan
    -1.09
    POSITIVE LOGITS
    に入れる
    1.27
     sám
    1.23
     trám
    1.21
     cortas
    1.12
     dát
    1.07
    ひた
    1.06
     musíte
    1.06
     Елена
    1.05
    着了
    1.05
    に挑戦
    1.04
    Activations Density 0.039%

    No Known Activations