© 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. 87222
    Prev
    Next
    INDEX
    Explanations

    Encyclopædia Britannica

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

    The neuron responds to semantically rich content words—particularly nouns and adjectives—while ignoring common function words and punctuation.

    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
     noastră
    -0.81
    ား
    -0.74
     recently
    -0.71
    choc
    -0.70
     reciente
    -0.70
     web
    -0.69
    ipelago
    -0.66
    हरु
    -0.66
    拥有
    -0.66
    Delay
    -0.66
    POSITIVE LOGITS
     Encyclopædia
    1.25
     Britannica
    1.24
     britann
    1.08
    Brit
    1.02
    Encyclopædia
    0.89
     Encyclopaedia
    0.88
     assail
    0.84
    brit
    0.84
     patrie
    0.81
    prende
    0.81
    Activations Density 0.022%

    No Known Activations