© 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. 67468
    Prev
    Next
    INDEX
    Explanations

    code block starters or separators

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

    The neuron is highly sensitive to 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
    શ
    -1.13
     revamped
    -1.07
    ellery
    -1.06
     chcia
    -1.05
     magnific
    -1.03
     actes
    -1.01
     berechnet
    -1.01
     zwischen
    -1.01
     também
    -1.00
    镲
    -1.00
    POSITIVE LOGITS
     with
    1.47
     where
    1.46
     as
    1.40
     after
    1.39
     while
    1.34
     still
    1.32
     on
    1.25
    ,
    1.23
     these
    1.20
     using
    1.20
    Activations Density 0.013%

    No Known Activations