© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115708
    Prev
    Next
    INDEX
    Explanations

    proper nouns and list separators

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

    The neuron fires on HTML/XML markup tokens (e.g. tags like `<br />` and entities like `&comma;`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     even
    -1.36
     unrelenting
    -1.17
     by
    -1.10
     autentic
    -1.09
     to
    -1.08
     it
    -1.07
    厦
    -1.06
     However
    -1.05
    Although
    -1.04
     tomate
    -1.04
    POSITIVE LOGITS
     ず
    1.18
     molti
    1.15
     tuturor
    1.14
     atractivo
    1.13
    ↵
    1.10
     abbildung
    1.05
     fahrrad
    1.03
    ఱ
    1.02
     calitate
    1.01
     vorbere
    1.00
    Activations Density 0.000%

    No Known Activations