© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48344
    Prev
    Next
    INDEX
    Explanations

    links and citations

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

    The neuron is tuned to detect numeric tokens (e.g. years, reference IDs, page numbers, and other digit sequences).

    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
    HMIS
    -0.83
     DOI
    -0.82
    hari
    -0.81
    mêmes
    -0.81
     Lib
    -0.80
     you
    -0.78
    holder
    -0.77
     claim
    -0.77
    μι
    -0.77
    ᾷ
    -0.75
    POSITIVE LOGITS
     apathy
    0.79
     fidget
    0.78
     unsus
    0.77
    írito
    0.76
    què
    0.75
    מל
    0.75
     איש
    0.75
     Hymns
    0.73
     palatable
    0.72
     unfore
    0.67
    Activations Density 0.002%

    No Known Activations