© 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. 108830
    Prev
    Next
    INDEX
    Explanations

    specific nouns following "the"

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

    The neuron flags content‐heavy, detail‐bearing terms (proper nouns, quantifiers, key nouns/adjectives, etc.) that carry the specific factual “meat” of a passage.

    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
    odend
    -1.12
     apparaissent
    -1.10
     čier
    -1.02
     jí
    -1.00
    шите
    -0.99
     mineures
    -0.98
     tijdens
    -0.98
     zů
    -0.96
     détru
    -0.95
     dám
    -0.94
    POSITIVE LOGITS
     said
    2.22
     different
    1.27
     same
    1.27
     latter
    1.24
     whole
    1.20
     recent
    1.13
     much
    1.11
     entire
    1.09
     mentioned
    1.06
     saying
    1.05
    Activations Density 0.023%

    No Known Activations