© 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. 65611
    Prev
    Next
    INDEX
    Explanations

    http:// or https://

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

    The neuron activates on the “http”/“https” protocol tokens at the start of URLs, i.e. it detects web links.

    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
    şek
    -1.53
    mohon
    -1.30
    geç
    -1.25
    daun
    -1.25
     silencioso
    -1.15
     DOMINGO
    -1.14
    josé
    -1.10
     JADX
    -1.08
     vás
    -1.07
    dü
    -1.05
    POSITIVE LOGITS
     tred
    1.07
    mostra
    1.06
     implor
    1.06
     accla
    1.05
     lamentable
    1.04
     reali
    1.03
     corpi
    1.02
     catac
    0.98
     offenbar
    0.98
     inconce
    0.97
    Activations Density 0.013%

    No Known Activations