© 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. 10-GEMMASCOPE-RES-131K
    4. 58791
    Prev
    Next
    INDEX
    Explanations

    database and programming contexts

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

    The neuron is tuned to pick up URL and domain name fragments (e.g. “http://”, “www”, “.com”, and similar web address tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     hanya
    -1.18
     apenas
    -1.08
     and
    -1.07
     on
    -1.05
     \%)$
    -1.03
    ","
    -1.03
     We
    -1.01
    \},
    -1.01
     sõ
    -1.00
     tanpa
    -0.98
    POSITIVE LOGITS
     cinematogra
    1.15
     впечатления
    1.13
     ſch
    1.09
     Bluffs
    1.09
     ananas
    1.09
     estante
    1.09
     Rises
    1.08
     gewi
    1.08
     detalló
    1.08
    它的
    1.04
    Activations Density 0.443%

    No Known Activations