© 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. 72615
    Prev
    Next
    INDEX
    Explanations

    urls and academic sites

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

    The neuron detects web‐address tokens (e.g. “https://”, “www.”, domain names) in the text.

    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
     jornalista
    -1.18
    panes
    -1.14
     caricatura
    -1.13
     stili
    -1.05
    thodoxy
    -1.05
     manda
    -1.04
     departament
    -1.04
    LayoutPanel
    -1.04
     from
    -1.04
     גם
    -1.04
    POSITIVE LOGITS
     идут
    1.04
    おわりに
    1.03
    icace
    1.03
     поможет
    1.01
     třeba
    1.00
    How
    0.98
    Learn
    0.96
    來看
    0.95
    ectl
    0.93
    Her
    0.93
    Activations Density 0.022%

    No Known Activations