© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60617
    Prev
    Next
    INDEX
    Explanations

    spatial transformations, positions, or object identifiers

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

    The neuron activates on numeric literals (numbers) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    拉着
    -1.66
    罍
    -1.51
     primeiros
    -1.49
    ’
    -1.41
    ︲
    -1.40
    ådet
    -1.37
     canais
    -1.35
     první
    -1.35
    ENDAR
    -1.34
    鹩
    -1.34
    POSITIVE LOGITS
    .
    1.88
     that
    1.65
    /
    1.52
    5
    1.51
    0
    1.51
     problems
    1.45
    3
    1.45
     one
    1.43
     including
    1.38
    著名
    1.38
    Activations Density 0.001%

    No Known Activations