© 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. 10-GEMMASCOPE-RES-131K
    7. 99524
    Prev
    Next
    INDEX
    Explanations

    cb callback or abbreviation

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

    The neuron fires on the token “cb,” i.e. occurrences of “cb” in identifiers or function names (often used as a callback shorthand).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    .
    -3.31
    Ꮞ
    -2.70
     erhielten
    -2.52
     nahmen
    -2.31
    Especificación
    -2.27
     retrô
    -2.25
    戬
    -2.13
    、“
    -2.11
     führten
    -2.11
     neuem
    -2.06
    POSITIVE LOGITS
     стал
    2.44
    ise
    2.20
    >
    2.17
    ed
    2.16
    ↵↵
    2.02
    ira
    2.02
    娘娘
    2.00
     связан
    1.99
     was
    1.98
     and
    1.95
    Activations Density 0.001%

    No Known Activations