© 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. 34-GEMMASCOPE-RES-131K
    7. 37981
    Prev
    Next
    INDEX
    Explanations

    technical nouns followed by verbs

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

    The neuron activates on specialized technical terms naming methods, devices, components, or materials (i.e. domain-specific nouns).

    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
    €“
    -1.05
    ‍♂
    -1.05
     erano
    -1.04
    weren
    -1.03
     arrivent
    -1.03
     lorsque
    -1.02
     récemment
    -1.02
     variados
    -1.02
     récomp
    -1.02
     lorsqu
    -1.02
    POSITIVE LOGITS
     could
    2.06
     is
    1.84
     was
    1.67
     can
    1.48
     would
    1.48
     seemed
    1.34
     mainly
    1.32
     still
    1.31
     surely
    1.30
     always
    1.30
    Activations Density 0.296%

    No Known Activations