© 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. 129078
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numerical measurement values (especially decimals) in technical specifications.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    variable physical properties

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     boissons
    -1.16
    ְּ
    -1.11
     feuilles
    -1.10
     lumières
    -1.10
    Wednesday
    -1.08
     jezt
    -1.07
     vieilles
    -1.06
    鲩
    -1.06
    いです
    -1.05
     бампер
    -1.05
    POSITIVE LOGITS
     desired
    1.63
     wanted
    1.48
     at
    1.36
     as
    1.29
     by
    1.22
     while
    1.22
     useful
    1.19
     but
    1.16
     can
    1.15
     or
    1.12
    Activations Density 0.195%

    No Known Activations