© 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. 22-GEMMASCOPE-RES-131K
    7. 27825
    Prev
    Next
    INDEX
    Explanations

    header file includes (.h)

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

    The neuron strongly activates on CamelCase code identifiers—especially file/module names in include or import statements (e.g. “NetworkInfoDlg.h,” “actor_jelly_bone.dart”).

    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
    olkata
    -1.16
     Verv
    -1.06
     with
    -1.05
    —
    -1.00
     by
    -0.91
    ,
    -0.91
    –
    -0.90
     nonostante
    -0.89
     again
    -0.89
     respective
    -0.88
    POSITIVE LOGITS
    maske
    1.13
    bringt
    1.09
    angere
    1.02
     beneficios
    1.02
     katk
    1.02
     citada
    1.01
    kritik
    1.01
     problemu
    1.00
     coucher
    0.99
    其它
    0.99
    Activations Density 0.008%

    No Known Activations