© 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. 10-GEMMASCOPE-RES-131K
    7. 42657
    Prev
    Next
    INDEX
    Explanations

    followed by articles or prepositions

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

    The neuron fires strongly on words carrying concrete, narrative-driven content—especially verbs (including participles) and nouns that describe action or change in a scene.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     hauptsächlich
    -2.45
     weitgehend
    -2.27
     you
    -2.17
     můžete
    -1.91
     témo
    -1.88
     hlavně
    -1.88
     focuses
    -1.84
     vorüber
    -1.83
     faudra
    -1.82
    Referenties
    -1.80
    POSITIVE LOGITS
    taya
    1.88
     maler
    1.80
     jeg
    1.71
     landes
    1.71
     serien
    1.69
     our
    1.69
     an
    1.66
    rrrrrr
    1.64
     funktion
    1.57
    tya
    1.57
    Activations Density 0.323%

    No Known Activations