© 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. 22-GEMMASCOPE-RES-131K
    7. 104537
    Prev
    Next
    INDEX
    Explanations

    scales and levels

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

    The neuron detects mentions of “scales” and scale-related modifiers (e.g. micro, meso, macro, various scales) 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
     verhind
    -1.24
     herbes
    -1.23
     trabalhadores
    -1.22
     шокола
    -1.22
     accueillir
    -1.21
    ittäin
    -1.17
     aján
    -1.16
    Proveedor
    -1.16
     ['./
    -1.13
     discuter
    -1.12
    POSITIVE LOGITS
     larger
    1.30
    coroutines
    1.25
     scale
    1.20
     we
    1.20
     information
    1.19
     macro
    1.16
     large
    1.09
     until
    1.05
     $
    1.02
    론
    1.02
    Activations Density 0.070%

    No Known Activations