© 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. 49750
    Prev
    Next
    INDEX
    Explanations

    time or quantity

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

    The neuron activates on numeric tokens, detecting numbers 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_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
     müm
    -1.24
     कैसी
    -1.20
     GRATIS
    -1.08
    folger
    -1.07
     atlet
    -1.05
     パンツ
    -1.04
     praktis
    -1.03
     transparentes
    -1.02
     cokelat
    -1.02
     meleg
    -1.02
    POSITIVE LOGITS
    osoever
    1.34
     каждо
    0.98
     namesake
    0.96
    当时的
    0.96
     пові
    0.95
    izzati
    0.94
     freaking
    0.94
    stdc
    0.94
    trums
    0.94
     funda
    0.93
    Activations Density 0.063%

    No Known Activations