© 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. 4259
    Prev
    Next
    INDEX
    Explanations

    daily weekly monthly offers

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

    The neuron is primarily firing on numeric tokens or quantitative/list‐style entries (e.g. numbers and things that look like list item headings).

    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
    真好
    -0.79
     argued
    -0.78
     diverted
    -0.78
     uncles
    -0.71
     registry
    -0.71
    疝
    -0.70
     Registry
    -0.70
     Topics
    -0.68
     kin
    -0.68
    registry
    -0.67
    POSITIVE LOGITS
     weekly
    1.39
     VIP
    1.35
     daily
    1.30
    VIP
    1.22
     reload
    1.20
     monthly
    1.19
     Monday
    1.16
     Reload
    1.14
     cashback
    1.11
    Reload
    1.06
    Activations Density 0.002%

    No Known Activations