© 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. 38549
    Prev
    Next
    INDEX
    Explanations

    words starting with "at"

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

    The neuron consistently activates on the subword “At,” i.e. instances of the token “At” at the start of words.

    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
    と
    -1.21
    や
    -1.06
    で
    -1.02
    ですが
    -0.97
    でも
    -0.94
    を
    -0.93
    ・
    -0.91
     probably
    -0.91
    ですね
    -0.90
     also
    -0.89
    POSITIVE LOGITS
     least
    1.63
    割と
    1.16
    つづく
    1.00
    凄く
    1.00
    って何
    0.99
    為に
    0.98
    を買う
    0.98
    warts
    0.97
     once
    0.97
     present
    0.96
    Activations Density 0.045%

    No Known Activations