© 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. 13882
    Prev
    Next
    INDEX
    Explanations

    `$` or `await` followed by `this`

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

    The neuron fires on numeric literal tokens (i.e. numbers) in source code.

    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
     not
    -1.50
     from
    -1.41
     first
    -1.35
    They
    -1.32
    These
    -1.30
    Those
    -1.30
     including
    -1.28
     two
    -1.27
    All
    -1.26
     to
    -1.24
    POSITIVE LOGITS
     our
    1.50
     you
    1.48
    
    1.44
     my
    1.43
     the
    1.41
     nimmer
    1.40
    menü
    1.32
     verhind
    1.32
     we
    1.31
    transferase
    1.29
    Activations Density 0.003%

    No Known Activations