© 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. 14160
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and equations

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

    The neuron flags numeric tokens and mathematical notation, i.e. digits, numbers, and equation symbols.

    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
     potenci
    -1.59
    Nichts
    -1.55
    реги
    -1.48
     arquite
    -1.43
    旁边的
    -1.40
     kommunik
    -1.39
    一旁的
    -1.39
     generell
    -1.35
     Desenvolvimento
    -1.35
     kelime
    -1.34
    POSITIVE LOGITS
     with
    1.45
     not
    1.39
     like
    1.36
     möchtest
    1.29
    !
    1.26
    才行
    1.25
     bibir
    1.23
     where
    1.21
     each
    1.18
     is
    1.16
    Activations Density 0.024%

    No Known Activations