© 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. 70632
    Prev
    Next
    INDEX
    Explanations

    terms, locations, and biology

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

    product or technology names like "iPod", "forex", "assembly", "Border Wall", "signal", "e-mail" and other specific technical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on the prominent “topic” words or key nouns that appear at the start of each new section or heading.

    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
    編曲
    -1.13
    thentication
    -1.09
    ÇÕES
    -1.08
    锛
    -1.06
    怎么回事
    -1.05
     seks
    -1.05
    Ɑ
    -1.03
     démission
    -1.02
    ствую
    -1.02
    borderSide
    -1.00
    POSITIVE LOGITS
     and
    1.45
     consape
    1.04
    _
    1.02
     sayfas
    0.96
     enhanced
    0.96
     so
    0.94
     one
    0.93
     wykonane
    0.93
     can
    0.91
     friendly
    0.91
    Activations Density 0.053%

    No Known Activations