© 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. 66214
    Prev
    Next
    INDEX
    Explanations

    License information

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

    The neuron detects numeric tokens (long sequences of digits, such as years, version numbers, and other multi‐digit numerals).

    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
     кило
    -0.78
    aneity
    -0.75
    >>>
    -0.74
    fillment
    -0.74
    bagi
    -0.73
     Tiere
    -0.73
    ׳
    -0.73
     giorno
    -0.73
    mulo
    -0.73
     schon
    -0.72
    POSITIVE LOGITS
    utta
    0.73
    いかがでしたか
    0.71
    推广
    0.69
     Cancell
    0.65
    こうして
    0.65
     ramb
    0.65
    vejte
    0.64
     Citadel
    0.64
     Ix
    0.63
    Unk
    0.63
    Activations Density 0.028%

    No Known Activations