© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49923
    Prev
    Next
    INDEX
    Explanations

    end of phrases

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

    The main thing this neuron does is detect content-bearing nouns and noun phrases (i.e. domain-specific or concrete entities) rather than function 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_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
     –
    -1.86
     -
    -1.69
     $-$
    -1.66
    ;
    -1.44
     --
    -1.36
     …
    -1.35
    快点
    -1.30
    %;
    -1.27
    --
    -1.25
     هذه
    -1.22
    POSITIVE LOGITS
     like
    1.57
     that
    1.53
     or
    1.48
     потому
    1.35
     in
    1.34
     didn
    1.31
     is
    1.27
     doesn
    1.26
    ？』
    1.21
     as
    1.20
    Activations Density 0.006%

    No Known Activations