© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35933
    Prev
    Next
    INDEX
    Explanations

    org/

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

    The neuron is strongly triggered by URL patterns (e.g. the “http://…org/licenses/…” sequence).

    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
     more
    -1.39
    siyah
    -1.21
     voulez
    -1.17
     those
    -1.15
    mudah
    -1.13
     intér
    -1.12
     such
    -1.11
     their
    -1.10
     all
    -1.09
     faits
    -1.06
    POSITIVE LOGITS
     ubi
    1.39
     aeroplane
    1.24
    Slik
    1.22
    Hilsen
    1.22
     odes
    1.12
    锲
    1.11
    Elin
    1.11
     merchan
    1.09
    Escrito
    1.08
    Moda
    1.06
    Activations Density 0.147%

    No Known Activations