© 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. 22-GEMMASCOPE-RES-131K
    7. 98615
    Prev
    Next
    INDEX
    Explanations

    redirecting to destination URL

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

    The neuron primarily detects numerical tokens or numeric literals (i.e., numbers and digits) 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_22/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
     abonnement
    -1.25
     rente
    -1.19
     rivi
    -1.18
     citroen
    -1.15
    illir
    -1.13
     inond
    -1.12
     volk
    -1.09
     kado
    -1.09
     appels
    -1.08
     pittores
    -1.06
    POSITIVE LOGITS
     after
    2.22
     on
    1.38
     после
    1.34
     destination
    1.28
     selepas
    1.27
    After
    1.27
    После
    1.22
     return
    1.21
     After
    1.20
     destinations
    1.19
    Activations Density 0.029%

    No Known Activations