© 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. 34-GEMMASCOPE-RES-131K
    7. 75863
    Prev
    Next
    INDEX
    Explanations

    linking details or consequences

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

    The neuron responds to numeric figures (digits) in the text, i.e. tokens representing 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_34/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
    😤
    -1.65
    😥
    -1.55
    🥵
    -1.55
    💞
    -1.53
    😠
    -1.51
    🙁
    -1.48
    😇
    -1.48
    _
    -1.46
    🤙
    -1.43
    😞
    -1.42
    POSITIVE LOGITS
     a
    2.50
     each
    2.38
     plenty
    2.25
     no
    2.25
     some
    2.05
     emphasis
    2.02
     lots
    1.92
     nothing
    1.90
     none
    1.85
     many
    1.80
    Activations Density 0.078%

    No Known Activations