© 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. 67066
    Prev
    Next
    INDEX
    Explanations

    identifiers and delimiters

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

    The neuron activates on programming identifier tokens—names of variables, types, imports, and similar 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
     dando
    -1.39
     ww
    -1.04
    wanna
    -1.03
    ffie
    -1.02
     cinq
    -1.01
    鼍
    -1.00
    maillot
    -1.00
     overarching
    -0.99
    oane
    -0.98
     branco
    -0.98
    POSITIVE LOGITS
     unique
    1.48
     uniquely
    1.40
     their
    1.30
     regardless
    1.20
     different
    1.19
     undeniably
    1.18
     nahezu
    1.17
    After
    1.17
     after
    1.12
     preventing
    1.07
    Activations Density 0.013%

    No Known Activations