© 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. 10-GEMMASCOPE-RES-131K
    7. 84529
    Prev
    Next
    INDEX
    Explanations

    code block terminators

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

    This neuron detects code lines that perform assignments—particularly property or variable assignment expressions ending with a semicolon.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ynchrotron
    -1.26
    をしました
    -1.25
     таких
    -1.24
     Erstellung
    -1.23
    вів
    -1.22
    aneers
    -1.22
     takich
    -1.21
    olves
    -1.20
     vários
    -1.19
     disgruntled
    -1.19
    POSITIVE LOGITS
     enables
    1.23
    0
    1.18
     genoemd
    1.18
     sizable
    1.16
     innumerable
    1.11
    пель
    1.11
     despite
    1.11
     facilitates
    1.10
     can
    1.10
    po
    1.10
    Activations Density 0.022%

    No Known Activations