© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40233
    Prev
    Next
    INDEX
    Explanations

    code element retrieval

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

    The neuron fires strongly on the opening parenthesis that begins a function or component call’s argument list 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_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
     it
    -1.96
     the
    -1.86
     its
    -1.48
    🧌
    -1.48
    になるので
    -1.44
    该如何
    -1.43
     그것
    -1.42
     or
    -1.41
     kostenlosen
    -1.38
    לם
    -1.34
    POSITIVE LOGITS
    ?
    1.66
    MAXN
    1.55
     most
    1.45
    +}$
    1.39
    *
    1.38
    
    1.35
    يف
    1.34
    ('=
    1.34
     –
    1.32
    <td>
    1.31
    Activations Density 0.103%

    No Known Activations