© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16703
    Prev
    Next
    INDEX
    Explanations

    names connected by and

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

    The neuron highlights standalone numeric tokens (especially three-digit numbers) in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    を
    -1.34
    その
    -1.24
    さらに
    -1.20
    なぜ
    -1.20
    それ
    -1.18
     Kategor
    -1.15
    ability
    -1.09
    与此同时
    -1.09
     LIABLE
    -1.09
    那
    -1.09
    POSITIVE LOGITS
    為に
    1.50
    ようです
    1.20
     These
    1.05
    scarpe
    1.05
    ためには
    1.01
    たびに
    1.01
     tieto
    0.99
    事が
    0.98
     opravdu
    0.98
    方がいい
    0.98
    Activations Density 0.011%

    No Known Activations