© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129400
    Prev
    Next
    INDEX
    Explanations

    The neuron is picking up internet domain and URL fragments (e.g. “.com,” “.net,” “.html,” email‐style domains).

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

    domain names and code elements

    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
     neumáticos
    -1.17
     vérification
    -1.09
     treinamento
    -1.09
     começaram
    -1.09
     prêmio
    -1.09
     плохо
    -1.07
    Ḥ
    -1.06
    擔心
    -1.05
    ...
    -1.05
     ситуация
    -1.04
    POSITIVE LOGITS
     after
    1.56
     or
    1.56
     and
    1.47
     at
    1.25
     with
    1.24
     of
    1.21
     through
    1.20
    Jahre
    1.20
     on
    1.19
     truly
    1.17
    Activations Density 0.000%

    No Known Activations