© 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. 10-GEMMASCOPE-RES-131K
    4. 42413
    Prev
    Next
    INDEX
    Explanations

    xhtml or imgur links

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

    The neuron strongly responds to technical protocol or format tokens (e.g. uppercase abbreviations like “UTF,” “XHTML,” domain names in URLs, charset declarations, and other markup‐related identifiers).

    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
     -
    -1.70
     also
    -1.56
    ല്‍
    -1.47
    IVENESS
    -1.38
     zostać
    -1.34
     Schicht
    -1.32
     including
    -1.30
     \
    -1.30
     —
    -1.30
     seule
    -1.28
    POSITIVE LOGITS
     the
    2.06
     it
    1.88
     its
    1.50
     anunció
    1.43
    fonds
    1.42
     nimmer
    1.36
     niektor
    1.33
     Kontexten
    1.30
     nachts
    1.29
    amerikanische
    1.29
    Activations Density 0.024%

    No Known Activations