© 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. 128415
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on technical identifiers or component/class names (e.g. PascalCase tokens) in code or error messages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical method names and queries

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     multiuso
    -1.27
     microfibra
    -1.21
    calciatore
    -1.15
    шила
    -1.13
    gangss
    -1.09
    zogen
    -1.05
     restera
    -1.05
     Gouver
    -1.05
     简介
    -1.05
    nexpected
    -1.05
    POSITIVE LOGITS
    res
    1.19
    co
    1.13
    ine
    1.09
    ns
    1.08
    Y
    1.07
    ​​
    1.06
     zentralen
    1.05
    mon
    1.03
     wodurch
    1.02
    R
    1.02
    Activations Density 0.000%

    No Known Activations