© 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. 10-GEMMASCOPE-RES-131K
    7. 11704
    Prev
    Next
    INDEX
    Explanations

    date / time indicators

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

    The neuron primarily activates on tokens containing numeric characters (i.e. it identifies 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_10/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
     vaih
    -1.63
     kertoo
    -1.57
     gangen
    -1.52
     mengangg
    -1.51
     middag
    -1.47
     klokken
    -1.45
     jäsen
    -1.42
     geda
    -1.42
    issä
    -1.41
     tämä
    -1.40
    POSITIVE LOGITS
    瞥
    1.27
    瞟
    1.23
    择
    1.22
     campesinos
    1.14
     do
    1.12
    捋
    1.12
     about
    1.09
     felt
    1.08
    业主
    1.08
    ):
    1.07
    Activations Density 0.668%

    No Known Activations