© 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. 70394
    Prev
    Next
    INDEX
    Explanations

    names, titles, and specific entities

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

    The neuron fires on isolated, title‐case or otherwise emphasized tokens that serve as section or list headings (e.g. the standalone capitalized words at the start of items).

    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
     also
    -1.16
     —
    -1.13
     producten
    -1.08
     também
    -1.07
     también
    -1.06
    ,—
    -1.01
    igenous
    -1.00
    也要
    -1.00
    というのも
    -0.97
    姿を
    -0.96
    POSITIVE LOGITS
    』『
    1.25
    「
    1.09
    ಗ
    1.05
     viable
    1.05
    ඨ
    1.02
     rightful
    1.01
    úť
    1.01
    rieren
    1.01
     first
    1.00
     overtly
    1.00
    Activations Density 0.025%

    No Known Activations