© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70432
    Prev
    Next
    INDEX
    Explanations

    numbers or variables in parentheses

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

    This neuron activates on numeric literals (numbers) in 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
    When
    -1.42
     of
    -1.23
    For
    -1.22
    Before
    -1.16
    With
    -1.15
     with
    -1.13
     When
    -1.05
    To
    -1.03
    Not
    -1.02
     when
    -1.02
    POSITIVE LOGITS
     astounding
    1.27
     ridiculously
    1.16
     kunnen
    1.13
     amazingly
    1.10
     astonishing
    1.10
    をしました
    1.09
     amazing
    1.09
    Açık
    1.09
    さっき
    1.09
    心中
    1.08
    Activations Density 0.010%

    No Known Activations