© 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. 68028
    Prev
    Next
    INDEX
    Explanations

    Neon Therapeutics

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

    numbers in mathematical sequences or numerical patterns.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric digits or multi‐digit numbers, marking positions where numbers appear (e.g. in sequences or math expressions).

    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
     altes
    -1.02
     located
    -0.98
    spania
    -0.98
     istot
    -0.96
     sized
    -0.95
     your
    -0.90
     approved
    -0.90
     on
    -0.90
     things
    -0.88
    classifiers
    -0.87
    POSITIVE LOGITS
     perfec
    1.18
    <bos>
    1.11
     paradis
    1.02
    Rü
    1.01
    caping
    1.01
    '>"
    1.01
    antism
    1.00
     AUSTR
    1.00
    Haber
    1.00
    Cade
    0.99
    Activations Density 0.004%

    No Known Activations