© 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. 22-GEMMASCOPE-RES-131K
    4. 84267
    Prev
    Next
    INDEX
    Explanations

    network data types and structures

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

    The neuron fires on numeric literals (e.g. standalone numbers, digits, or numeric values) 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_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
     their
    -1.30
    vaných
    -1.02
    menn
    -0.94
    дии
    -0.94
     妹
    -0.91
    慨
    -0.91
     perros
    -0.91
    عود
    -0.91
     this
    -0.90
     cepillo
    -0.90
    POSITIVE LOGITS
    MODO
    1.10
     sentimento
    1.08
    Requiem
    1.03
    ቶ
    0.98
    eraard
    0.98
     fenô
    0.97
     Requiem
    0.95
     cérebro
    0.95
     invas
    0.93
     extravag
    0.92
    Activations Density 0.008%

    No Known Activations