© 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. 129085
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on programming configuration keys—especially “headers” (and related config labels).

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

    key: value assignments

    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
     of
    -1.48
     anyone
    -1.27
     Any
    -1.18
     comes
    -1.14
     its
    -1.13
     would
    -1.12
     could
    -1.12
     Anyone
    -1.11
     any
    -1.11
     Would
    -1.06
    POSITIVE LOGITS
    میزی
    1.16
     nuest
    1.16
     тук
    1.10
    ：
    1.07
    Kerala
    1.02
     velg
    1.02
     Funda
    0.99
     gallina
    0.98
     paulo
    0.98
    。
    0.98
    Activations Density 0.001%

    No Known Activations