© 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. 24943
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    The neuron is looking for numerical literals—especially multi‐digit numbers and decimal (floating-point) values in code or data.

    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
    他就
    -1.23
     Therefore
    -1.23
     dicha
    -1.20
     Рекоменду
    -1.20
    づけ
    -1.17
    ようです
    -1.15
     Moreover
    -1.15
     The
    -1.13
     Gesetze
    -1.13
     beobachten
    -1.10
    POSITIVE LOGITS
    を
    1.55
    方針
    1.45
    って思
    1.38
    oys
    1.23
    もある
    1.22
    態度
    1.21
     Felic
    1.20
    が
    1.17
     optik
    1.17
    thirds
    1.17
    Activations Density 0.006%

    No Known Activations