© 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. 129823
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to numeric tokens—digits or number sequences such as phone numbers, dates, ages, measurements, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    psychotic, Q:, letter, high

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Création
    -1.22
     garantía
    -1.09
     
    -1.08
     東京都
    -1.03
    に挑戦
    -1.02
     timmar
    -1.02
    ležité
    -1.00
     increíbles
    -0.99
    Professor
    -0.99
    Council
    -0.98
    POSITIVE LOGITS
     with
    1.51
    Sinopse
    1.41
     также
    1.25
    ныя
    1.24
     wartawan
    1.23
     aperto
    1.23
    надца
    1.22
     vincere
    1.19
     crescere
    1.14
     after
    1.13
    Activations Density 0.000%

    No Known Activations