© 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. 10-GEMMASCOPE-RES-131K
    7. 8673
    Prev
    Next
    INDEX
    Explanations

    new rule or filter operator

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

    The neuron is keyed to programming‐style punctuation and structural tokens—things like commas, braces, and indentation in code.

    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
    譬
    -1.18
     DIFFERENT
    -1.12
     подоб
    -1.06
     Escribe
    -1.05
    different
    -1.05
    kannt
    -1.05
    そうに
    -1.05
     exatamente
    -1.03
     exactement
    -1.02
     esattamente
    -1.02
    POSITIVE LOGITS
     as
    1.39
     all
    1.38
     aspects
    1.34
    ]))
    1.29
     essential
    1.25
     basic
    1.23
    EFIAPI
    1.22
     todas
    1.21
    amentul
    1.20
     over
    1.19
    Activations Density 0.136%

    No Known Activations