© 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. 22-GEMMASCOPE-RES-131K
    7. 10934
    Prev
    Next
    INDEX
    Explanations

    web store, app, guidelines

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

    The neuron fires on standalone numeric tokens (pure numbers) in equations or technical/math contexts.

    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
     mxArray
    -0.93
     kerusakan
    -0.91
    czyć
    -0.88
     pagine
    -0.87
     võib
    -0.87
     userModel
    -0.87
     бампер
    -0.86
    ೞ
    -0.86
     dati
    -0.85
     anpass
    -0.85
    POSITIVE LOGITS
     gelukkig
    1.16
     meteen
    1.15
     hermosas
    1.14
     tevens
    1.10
     meestal
    1.09
     geweldig
    1.08
     trabajando
    1.04
     cualquier
    1.04
     waarschijnlijk
    1.03
     will
    1.02
    Activations Density 0.004%

    No Known Activations