© 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. 2377
    Prev
    Next
    INDEX
    Explanations

    locations and rooms

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

    The main thing this neuron does is detect numeric tokens (multi-digit numbers and counts) 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_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
    MÁS
    -0.79
    Edición
    -0.78
     six
    -0.78
    了起来
    -0.74
     from
    -0.73
    pousada
    -0.73
     labdar
    -0.73
    tapis
    -0.72
    ندن
    -0.72
     seven
    -0.72
    POSITIVE LOGITS
     hotel
    1.36
     office
    1.34
     corridor
    1.20
     hotels
    1.12
     cafe
    1.10
     entrance
    1.09
     hotelu
    1.08
    entrée
    1.06
     coffee
    1.05
     corridors
    1.05
    Activations Density 0.006%

    No Known Activations