© 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. 34-GEMMASCOPE-RES-131K
    7. 109246
    Prev
    Next
    INDEX
    Explanations

    compound interest or growth

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

    The neuron primarily detects numeric tokens and sequences (digits, percentages, and other number-related strings).

    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
    mdb
    -0.78
     romantic
    -0.76
    姆
    -0.71
    romantic
    -0.68
    Shelf
    -0.66
     síntomas
    -0.65
     ता
    -0.65
    hashi
    -0.64
    าม
    -0.63
     mits
    -0.63
    POSITIVE LOGITS
     compound
    5.94
    compound
    5.22
    Compound
    5.13
     compounding
    5.06
     Compound
    4.91
     compounded
    4.72
     COMPOUND
    4.47
     compounds
    4.28
     Compounds
    3.66
     COMPOUNDS
    2.83
    Activations Density 0.056%

    No Known Activations