© 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. 130204
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on tokens serving as keys or type labels immediately adjacent to a colon (e.g. “int:” or “vector:” in code/config declarations).

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

    programmatic identifiers followed by values

    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
     copos
    -1.31
     blusa
    -1.22
     asfalto
    -1.18
     médias
    -1.15
     évé
    -1.14
     entweder
    -1.10
     azulejos
    -1.09
     abbildung
    -1.09
     márm
    -1.04
    leges
    -1.04
    POSITIVE LOGITS
    !
    1.24
    b
    1.23
    w
    1.13
    que
    1.09
    жении
    1.06
     Wohnzimmer
    1.05
    y
    1.05
     ['./
    1.05
    by
    1.04
     sabid
    1.03
    Activations Density 0.001%

    No Known Activations