© 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. 95603
    Prev
    Next
    INDEX
    Explanations

    pronoun or subject followed by verb

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

    This neuron fires on the main promotional or sales statements—typically the opening words of advertising copy where a company or product is being introduced (e.g. “Our,” “We,” “It,” “They”).

    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
     more
    -1.45
     before
    -1.41
     during
    -1.33
     subsequently
    -1.32
     after
    -1.31
     at
    -1.27
     other
    -1.25
     or
    -1.23
     their
    -1.21
     also
    -1.21
    POSITIVE LOGITS
    不仅
    1.38
    不但
    1.38
     formules
    1.30
     persil
    1.30
     maux
    1.28
    帏
    1.26
    Already
    1.23
     astu
    1.22
     certes
    1.22
     antik
    1.21
    Activations Density 0.094%

    No Known Activations