© 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. 34-GEMMASCOPE-RES-131K
    7. 49343
    Prev
    Next
    INDEX
    Explanations

    such and other

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

    The neuron activates on tokens representing numbers or numeric values (e.g. years, prices, counts).

    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
    页面存档备份
    -0.95
     själva
    -0.88
    chorus
    -0.87
    但却
    -0.85
     dieselben
    -0.84
     logarithms
    -0.84
    ❤❤
    -0.81
    muñ
    -0.81
    cherichia
    -0.81
    🌸
    -0.81
    POSITIVE LOGITS
     things
    3.00
     stuff
    2.48
     such
    2.42
     phenomena
    2.30
     items
    2.27
     topics
    2.23
     entities
    2.17
     olyan
    2.17
     places
    2.06
     таких
    2.05
    Activations Density 0.215%

    No Known Activations