© 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. 75806
    Prev
    Next
    INDEX
    Explanations

    code and data structures

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

    The neuron strongly fires on numeric tokens and other tokens containing or representing numbers.

    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
    routines
    -0.69
    quote
    -0.69
     nghiệp
    -0.69
     practices
    -0.68
     إلي
    -0.67
     reverber
    -0.67
     cường
    -0.66
     quote
    -0.66
     Sistemas
    -0.66
    ひ
    -0.66
    POSITIVE LOGITS
    ktur
    0.68
    ﻲ
    0.68
    etree
    0.67
    すじ
    0.65
    Welt
    0.64
     Window
    0.62
     precon
    0.61
    Morph
    0.60
    guide
    0.60
    attes
    0.60
    Activations Density 0.051%

    No Known Activations