© 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. 111179
    Prev
    Next
    INDEX
    Explanations

    also and similar words

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

    The neuron is primarily triggered by numeric tokens and number‐like sequences (e.g. version numbers, measurements, IDs).

    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
     SEVENTH
    -1.40
     EGYPT
    -1.38
     WELFARE
    -1.37
    ↵
    -1.29
    licopter
    -1.28
     FIFTH
    -1.27
     palazzo
    -1.27
     LUMI
    -1.23
     if
    -1.22
     submar
    -1.22
    POSITIVE LOGITS
     also
    1.50
    Also
    1.47
     также
    1.30
    znám
    1.26
    臥
    1.23
     también
    1.23
     recently
    1.22
     également
    1.21
    They
    1.18
    toDouble
    1.17
    Activations Density 0.477%

    No Known Activations