© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93404
    Prev
    Next
    INDEX
    Explanations

    describing conditions or consequences

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

    The neuron activates on numeric expressions—particularly decimal numbers—wherever they occur in the 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_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
     They
    -1.38
     frequentemente
    -1.26
     trésor
    -1.23
     cinquième
    -1.18
    ických
    -1.18
    annt
    -1.17
    ⃰
    -1.16
     lesquelles
    -1.14
     nœ
    -1.14
     แต่
    -1.13
    POSITIVE LOGITS
     in
    1.55
     -
    1.25
     when
    1.20
     regarding
    1.20
     other
    1.20
     internetowa
    1.19
     amidst
    1.13
     on
    1.12
     –
    1.10
     whose
    1.08
    Activations Density 0.013%

    No Known Activations