© 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. 117585
    Prev
    Next
    INDEX
    Explanations

    email addresses and URLs

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

    The neuron fires on URL and email address components—especially top‐level domain tokens (e.g. “com,” “org,” “gov”), protocol markers (“https”), and related URL fragments.

    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
     that
    -1.84
    ~
    -1.20
     this
    -1.19
    ---
    -1.12
    —
    -1.11
    --
    -1.06
    :
    -1.05
     has
    -1.05
     That
    -1.05
     is
    -1.03
    POSITIVE LOGITS
     or
    1.96
    或是
    1.45
    }$.
    1.38
    ‪.‬‬
    1.35
     and
    1.34
     oppure
    1.31
    あるいは
    1.29
    或者是
    1.25
     gdzie
    1.23
    もしくは
    1.23
    Activations Density 0.045%

    No Known Activations