© 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. 82715
    Prev
    Next
    INDEX
    Explanations

    base or pedestal

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

    The neuron is tuned to detect numeric expressions (digits and measurements) 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
    pogon
    -0.90
    ographs
    -0.88
    никюр
    -0.81
    webe
    -0.80
    endgroup
    -0.79
    dibles
    -0.78
    τικός
    -0.77
    ceiling
    -0.76
    followed
    -0.74
     shutters
    -0.74
    POSITIVE LOGITS
     base
    3.61
    base
    2.92
     bases
    2.78
     Base
    2.66
    Base
    2.45
    BASE
    2.38
     BASE
    2.36
     pedestal
    2.28
     Bases
    2.27
    基
    2.02
    Activations Density 0.034%

    No Known Activations