© 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. 71351
    Prev
    Next
    INDEX
    Explanations

    programming code and scientific concepts

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

    This neuron specializes in spotting programming‐style tokens—identifiers, operators, and punctuation typical of code snippets.

    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
     still
    -1.16
    ﻹ
    -1.13
    ایان
    -1.09
     Darts
    -1.07
    日発売
    -1.03
    iotensin
    -1.02
    اهر
    -1.00
    aménagement
    -0.99
    ឋ
    -0.99
    年には
    -0.98
    POSITIVE LOGITS
     play
    1.09
     you
    1.09
     ensuing
    1.07
     entrambi
    1.05
    美味しかった
    1.03
    logique
    0.97
    BERTO
    0.93
     passiert
    0.92
    Curtir
    0.92
    homonymie
    0.92
    Activations Density 0.000%

    No Known Activations