© 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. 34-GEMMASCOPE-RES-131K
    7. 1866
    Prev
    Next
    INDEX
    Explanations

    blog metaweblog OpenID

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

    The neuron strongly activates on uppercase technical acronyms and initialisms (e.g. RPC, XML, ID, URLs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Facebook
    -1.11
     Facebook
    -1.00
    facebook
    -0.97
     facebook
    -0.89
     ۲۰۱
    -0.88
    Youtube
    -0.82
     imgur
    -0.78
     FACEBOOK
    -0.77
    newBuilder
    -0.75
    aży
    -0.74
    POSITIVE LOGITS
     Blogger
    0.96
    Synd
    0.95
     blogging
    0.93
    openid
    0.87
    synd
    0.83
    blog
    0.82
     bloggers
    0.81
     publishing
    0.81
     micro
    0.81
     Gruber
    0.81
    Activations Density 0.157%

    No Known Activations