© 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. 67638
    Prev
    Next
    INDEX
    Explanations

    compound nouns

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

    The neuron fires strongly on the main topic noun of a section or title—i.e. the key domain‐specific word that names what the passage is about.

    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
    ném
    -1.20
    』(
    -1.17
    嶸
    -1.13
    מבר
    -1.11
     Это
    -1.10
    Datuak
    -1.08
    naie
    -1.07
     pól
    -1.05
     anivers
    -1.05
    ayangkan
    -1.05
    POSITIVE LOGITS
    o
    1.30
    x
    1.28
    v
    1.20
     '
    1.18
    u
    1.16
    s
    1.14
    p
    1.09
    —
    1.07
    c
    1.07
     "
    1.05
    Activations Density 0.228%

    No Known Activations