© 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. 738
    Prev
    Next
    INDEX
    Explanations

    names ending in un

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

    The neuron responds to numeric tokens (digits and 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
    ädig
    -0.88
     bleek
    -0.74
    WriteHeader
    -0.74
     Cherokee
    -0.74
     Bart
    -0.73
    intang
    -0.72
    udu
    -0.72
    Étape
    -0.72
    CreateInfo
    -0.71
    ଆ
    -0.70
    POSITIVE LOGITS
     bun
    1.32
     buns
    1.18
     Dunn
    1.16
    Sun
    1.16
    bun
    1.13
    Dunn
    1.11
     bunk
    1.09
    mun
    1.09
    fun
    1.09
     hun
    1.06
    Activations Density 0.044%

    No Known Activations