© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77083
    Prev
    Next
    INDEX
    Explanations

    names of people and places

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

    The neuron selectively responds to tokens that appear in formal, news‐article or legal‐style prose (e.g. headlines, datelines and case citations).

    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
     microbiome
    -1.67
     livestream
    -1.46
     CRISPR
    -1.41
     millennials
    -1.38
     graphene
    -1.37
     LGBTQ
    -1.34
     vaping
    -1.33
     YouTuber
    -1.31
     selfie
    -1.25
     podcasts
    -1.25
    POSITIVE LOGITS
     then
    1.24
     numerous
    1.23
     both
    1.22
     several
    1.22
     this
    1.16
     what
    1.16
     old
    1.14
     three
    1.13
     other
    1.13
     even
    1.12
    Activations Density 0.257%

    No Known Activations