© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58844
    Prev
    Next
    INDEX
    Explanations

    describes a state or property

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

    The neuron strongly fires on copular linking verbs (e.g. “is,” “are,” “It is,” “They are”) that introduce definitional or descriptive statements.

    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
     будут
    -1.35
     بودند
    -1.27
    ētu
    -1.16
    ходили
    -1.13
     خواهند
    -1.09
    álna
    -1.09
     میکنم
    -1.09
     میکنه
    -1.09
     ར
    -1.07
     fichero
    -1.02
    POSITIVE LOGITS
     is
    3.20
     was
    2.41
     can
    2.27
     has
    2.11
     been
    1.47
     gained
    1.43
     are
    1.41
    还可以
    1.38
     also
    1.30
    也可以
    1.25
    Activations Density 0.358%

    No Known Activations