© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75380
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    This neuron responds to programming‐oriented identifiers and technical keywords (e.g. library/class names, code symbols).

    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
     Work
    -0.82
    blox
    -0.81
     la
    -0.81
    placements
    -0.79
    cxx
    -0.78
     pea
    -0.78
    aways
    -0.77
     ecstatic
    -0.77
    diyah
    -0.76
     bro
    -0.74
    POSITIVE LOGITS
     again
    1.30
    again
    1.14
    一樣
    1.12
     novamente
    1.09
     снова
    1.09
     same
    1.03
    AGAIN
    1.01
     opět
    1.00
    Again
    0.99
     seite
    0.98
    Activations Density 0.019%

    No Known Activations