© 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. 68004
    Prev
    Next
    INDEX
    Explanations

    programming and specific entities

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

    This neuron primarily activates on code identifiers (class/type/method names and other programming tokens).

    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
     or
    -1.20
    лили
    -1.15
    Технические
    -1.15
    KeyStore
    -1.12
    pters
    -1.09
     могли
    -1.09
     appré
    -1.08
     réuss
    -1.07
    OrBuilder
    -1.05
    bitField
    -1.05
    POSITIVE LOGITS
     verurs
    1.13
    岽
    1.08
     return
    1.01
     Ursache
    1.00
    distingu
    1.00
     이름
    0.99
     внутріш
    0.99
    tiara
    0.95
     online
    0.95
     Как
    0.95
    Activations Density 1.145%

    No Known Activations