© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10960
    Prev
    Next
    INDEX
    Explanations

    coding with jQuery and JavaScript

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

    variable assignment operators (equals signs) in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron never fires on any of the example tokens—it’s effectively “dead” (i.e. it doesn’t detect any pattern in these inputs).

    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
    ing
    -1.25
    right
    -1.19
    },
    -1.13
    mark
    -1.12
    tion
    -1.12
    ‟
    -1.11
     telling
    -1.10
    ell
    -1.09
    op
    -1.09
    ride
    -1.09
    POSITIVE LOGITS
     keindahan
    1.41
     latihan
    1.32
     tugas
    1.30
     nemá
    1.29
     vetores
    1.27
     vanske
    1.27
     meskipun
    1.26
     Testamento
    1.25
     pilihan
    1.24
    或
    1.23
    Activations Density 0.041%

    No Known Activations