© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62732
    Prev
    Next
    INDEX
    Explanations

    articles and determiners

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

    The neuron fires on causal and temporal cues in legal‐news prose—especially past‐event verbs (overturned, stemmed, triggered) and linking words (when, came, as a result of, during) that describe how court actions unfolded.

    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
     you
    -1.44
     these
    -1.23
     veľa
    -1.23
    nejšie
    -1.21
     adecuada
    -1.20
     utilizada
    -1.19
     it
    -1.19
    poptosis
    -1.15
     estekak
    -1.14
    raujo
    -1.13
    POSITIVE LOGITS
     a
    5.50
     an
    3.23
     একটি
    2.23
     sebuah
    2.06
    一个
    1.84
     einer
    1.84
     μια
    1.74
    了一個
    1.68
     einem
    1.61
     two
    1.59
    Activations Density 0.317%

    No Known Activations