© 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. 25862
    Prev
    Next
    INDEX
    Explanations

    code blocks and arrow functions

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

    The neuron fires on occurrences of the Ruby “do” keyword used to open code blocks.

    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
    providedIn
    -1.66
     Many
    -1.23
     and
    -1.21
    ;%%
    -1.18
    数百
    -1.17
    ğu
    -1.16
     Before
    -1.16
     untuk
    -1.16
    数十
    -1.16
     serta
    -1.14
    POSITIVE LOGITS
     potência
    1.24
     kolejny
    1.09
    心灵
    1.09
     моей
    1.07
    透过
    1.06
    菒
    1.05
    繊細
    1.05
     níveis
    1.05
    or
    1.03
     passar
    1.03
    Activations Density 0.003%

    No Known Activations