© 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. 103499
    Prev
    Next
    INDEX
    Explanations

    past states or actions

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

    The neuron fires strongly on anatomical or morphological descriptors—especially body-part terms (like “pairs,” “pods,” “spines”) used to detail an organism’s structure.

    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
     became
    -1.17
     found
    -1.11
     ended
    -1.05
     started
    -1.04
     decided
    -1.00
     got
    -0.99
     discovered
    -0.95
     commenced
    -0.90
     began
    -0.87
     оказалось
    -0.87
    POSITIVE LOGITS
     operated
    1.33
     functioned
    1.23
    operated
    1.23
     wore
    1.19
     relied
    1.13
    っていた
    1.11
     بوده
    1.06
     lived
    1.05
    にあった
    1.03
     catered
    1.02
    Activations Density 0.122%

    No Known Activations