© 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. 65418
    Prev
    Next
    INDEX
    Explanations

    technical prefixes and abbreviations

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

    The neuron fires on code‐identifier fragments—especially short acronyms or name parts (module/ns/struct prefixes, constants, etc.) in source 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
     lustige
    -1.06
    nyata
    -1.00
     Keuangan
    -0.93
     linken
    -0.92
     this
    -0.92
    พาะ
    -0.90
     ayaa
    -0.90
     муніципалі
    -0.89
     hvis
    -0.88
    mıştır
    -0.87
    POSITIVE LOGITS
     gtr
    1.02
     cvt
    1.02
     справи
    0.97
    踹
    0.92
    or
    0.89
     INFIN
    0.89
    arthed
    0.88
    *>
    0.87
    EL
    0.87
    <th>
    0.87
    Activations Density 0.014%

    No Known Activations