© 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. 13854
    Prev
    Next
    INDEX
    Explanations

    eigenvalues and eigenvectors

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

    The neuron fires on numeric tokens (digit sequences and numbers, including integers and decimals).

    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
     preguntar
    -1.13
     effectuer
    -1.12
     なお
    -1.09
    %)$
    -1.09
     purchases
    -1.05
     sauce
    -1.02
    охо
    -1.02
     تصریح
    -1.01
     durante
    -1.00
    ýl
    -1.00
    POSITIVE LOGITS
     eigenvalues
    1.37
     first
    1.11
     with
    1.10
    穩定
    1.06
    ߣ
    1.05
    isolate
    1.02
     място
    1.01
     some
    1.01
     those
    0.98
    bảng
    0.98
    Activations Density 0.030%

    No Known Activations