© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11051
    Prev
    Next
    INDEX
    Explanations

    error reporting and debugging

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

    The neuron responds to numeric literal tokens (i.e. numbers in the code).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    為に
    -1.34
    愠
    -1.19
    visite
    -1.16
    -¡
    -1.15
     împre
    -1.14
    "/"
    -1.13
    ghana
    -1.13
     Также
    -1.11
    ncc
    -1.10
    筈
    -1.10
    POSITIVE LOGITS
    4
    1.50
    3
    1.35
    what
    1.35
    new
    1.29
    excellents
    1.28
    e
    1.27
     What
    1.26
     what
    1.24
    5
    1.24
     какая
    1.22
    Activations Density 0.001%

    No Known Activations