© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65698
    Prev
    Next
    INDEX
    Explanations

    specifications

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

    The neuron fires on tokens that are part of header‐file include paths (i.e. filenames and “.h” components in `#include` or similar import/include statements).

    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
     luxus
    -1.01
     fichiers
    -0.98
    
    -0.97
     angiel
    -0.96
     ὁ
    -0.94
    hopefully
    -0.94
    wouldn
    -0.93
    xxxxx
    -0.93
     ΤΟ
    -0.92
     horloge
    -0.92
    POSITIVE LOGITS
     for
    0.93
     if
    0.89
     like
    0.87
     If
    0.86
     crafted
    0.85
     extended
    0.84
    种类
    0.83
     specific
    0.83
     reason
    0.82
     additional
    0.81
    Activations Density 0.012%

    No Known Activations