© 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. 10-GEMMASCOPE-RES-131K
    7. 124677
    Prev
    Next
    INDEX
    Explanations

    that to

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

    The neuron specializes in detecting numeric tokens (integers or decimals) wherever they appear 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_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
     sebagainya
    -1.39
     which
    -1.36
     soldadura
    -1.26
    𝘎
    -1.21
     selera
    -1.21
     milyen
    -1.21
     onderdelen
    -1.21
    閬
    -1.20
     įva
    -1.20
    sistente
    -1.19
    POSITIVE LOGITS
    はこんな感じ
    1.44
     тези
    1.33
     Nonetheless
    1.32
    </i>
    1.29
     :
    1.27
    acjach
    1.23
     águas
    1.22
     musisz
    1.20
    藐
    1.20
    /
    1.14
    Activations Density 0.057%

    No Known Activations