© 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. 22-GEMMASCOPE-RES-131K
    4. 104282
    Prev
    Next
    INDEX
    Explanations

    either/both options

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

    The neuron fires on domain-specific jargon or named technical terms (e.g. chemical names, competition stages, model identifiers) rather than ordinary words.

    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
    然后
    -0.84
     very
    -0.84
     after
    -0.83
    Bardzo
    -0.82
     eliminare
    -0.81
    𝒦
    -0.81
    Enfant
    -0.81
    osexuality
    -0.79
     ponemos
    -0.78
     حول
    -0.78
    POSITIVE LOGITS
     both
    1.44
     either
    1.37
     både
    1.24
    both
    1.16
    minmax
    1.08
    无论是
    1.07
     zarówno
    1.04
    ทั้ง
    1.02
     zowel
    1.00
    either
    0.99
    Activations Density 0.083%

    No Known Activations