© 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. 104491
    Prev
    Next
    INDEX
    Explanations

    compare numbers enclosed by parentheses

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

    The neuron detects numeric tokens, especially multi-digit numbers.

    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
     not
    -1.12
    țiuni
    -0.96
    страция
    -0.96
    >?
    -0.90
     bicarbonate
    -0.88
     meerdere
    -0.88
     tém
    -0.85
     hogyan
    -0.85
     Japão
    -0.85
     louder
    -0.85
    POSITIVE LOGITS
     ответил
    0.88
    还好
    0.87
    even
    0.85
    pertina
    0.84
    ICOLON
    0.84
    ふり
    0.83
    chanan
    0.83
     slightest
    0.82
     спросил
    0.82
    task
    0.81
    Activations Density 0.021%

    No Known Activations