© 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. 58690
    Prev
    Next
    INDEX
    Explanations

    organizational or physical entities

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

    The neuron fires strongly on technical/mechanical nouns referring to devices, components, or engineered systems.

    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
    里有
    -1.01
    coloriage
    -0.98
    muslim
    -0.96
     жы
    -0.92
    就不是
    -0.91
    ܆
    -0.91
     cóc
    -0.91
     gosta
    -0.91
    摒
    -0.91
     funcionamento
    -0.90
    POSITIVE LOGITS
     itself
    2.38
     or
    2.22
     you
    1.73
     concerned
    1.41
     Itself
    1.36
     chosen
    1.31
    টি
    1.30
    itself
    1.26
     they
    1.22
     youre
    1.20
    Activations Density 0.218%

    No Known Activations