© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66264
    Prev
    Next
    INDEX
    Explanations

    symbols or variables followed by 'is'

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

    The neuron responds to isolated mathematical symbols and variable names (single‐letter or short alphanumeric tokens used in formulas).

    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
     każdym
    -1.19
     Fußballspieler
    -1.15
     Schriftsteller
    -1.08
     habrían
    -1.08
     (!__
    -1.05
     außerdem
    -1.05
     मुझे
    -1.02
    banez
    -1.01
     conclusiones
    -1.00
     cambian
    -1.00
    POSITIVE LOGITS
     is
    1.73
     was
    1.24
     can
    1.23
     are
    1.19
     =
    1.19
    は
    1.16
    '
    1.09
     (
    1.09
     fyra
    1.05
     pengar
    1.02
    Activations Density 0.017%

    No Known Activations