© 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. 75219
    Prev
    Next
    INDEX
    Explanations

    .S// LicensedA VISUALLY

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

    This neuron flags tokens made up entirely of digits or pure punctuation (e.g. numeric strings and “.”).

    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
     muze
    -1.32
     galeri
    -1.31
     stát
    -1.26
     majest
    -1.26
     palais
    -1.24
     kafe
    -1.23
     labdar
    -1.21
     Fórmula
    -1.19
     douane
    -1.19
     panik
    -1.16
    POSITIVE LOGITS
     at
    1.46
     многие
    1.21
     you
    1.21
     one
    1.09
     kệ
    1.07
     K
    1.05
     also
    1.05
     with
    1.05
      
    1.04
    立派
    1.04
    Activations Density 0.000%

    No Known Activations