© 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. 65089
    Prev
    Next
    INDEX
    Explanations

    class/configuration/party/introduction

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

    The neuron fires on standalone technology or framework identifiers (e.g. SpringBoot, Application, Configuration, Flask).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    dmg
    -1.17
    ejo
    -1.16
    kursi
    -1.16
    Cechy
    -1.12
    ----</
    -1.10
    damen
    -1.08
    baño
    -1.07
    scienced
    -1.06
    -------------</
    -1.06
    estä
    -1.05
    POSITIVE LOGITS
    1
    1.24
    6
    1.20
    2
    1.17
    3
    1.14
    5
    1.07
    1.05
    4
    1.05
    If
    1.05
    擁有
    1.02
    ociação
    1.01
    Activations Density 0.000%
    No Known Activations