© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15280
    Prev
    Next
    INDEX
    Explanations

    amenities and civic buildings

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

    The neuron is keyed to any numeric token or measurement (e.g. integers, decimals, statistics) in the text.

    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
     either
    -1.48
     spôso
    -1.27
     zowel
    -1.23
    archiwizowane
    -1.23
    ITHER
    -1.22
    マジで
    -1.20
     โดย
    -1.19
     verhind
    -1.19
    任何
    -1.19
     vícti
    -1.18
    POSITIVE LOGITS
    cillary
    1.19
    کہ
    1.10
    謎
    1.08
     rénovation
    1.07
     entertainment
    1.05
     administra
    1.03
     a
    1.02
    🚰
    1.02
     chiesa
    1.01
     宣传
    0.99
    Activations Density 0.037%

    No Known Activations