© 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. 22-GEMMASCOPE-RES-131K
    7. 39236
    Prev
    Next
    INDEX
    Explanations

    international words and phrases

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

    The neuron is keyed to common prepositional “linking” phrases—e.g. it lights up on tokens like “in” when they form phrases such as “in consultation with” or “for example.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     our
    -1.14
     потому
    -1.13
     because
    -1.10
     overall
    -1.09
     poiché
    -1.09
    については
    -1.00
    でしょうね
    -1.00
    それでは
    -0.99
     aceptas
    -0.99
    それにしても
    -0.98
    POSITIVE LOGITS
    度は
    1.06
     své
    1.04
     свои
    1.04
    july
    1.02
    cherichia
    1.00
    acruz
    0.98
     своим
    0.98
     through
    0.98
    ุต
    0.95
    ти
    0.94
    Activations Density 0.040%

    No Known Activations