© 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. 6780
    Prev
    Next
    INDEX
    Explanations

    to keep, to provide, to pursue

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

    The neuron detects first‐person expressions of personal desire or intent (e.g. “I would like to …”).

    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
     никаких
    -1.27
     etwa
    -1.22
     notamment
    -1.21
     :/
    -1.14
     fiable
    -1.11
     distintos
    -1.10
     namens
    -1.08
     ethos
    -1.07
     tryna
    -1.06
     embodying
    -1.05
    POSITIVE LOGITS
     veramente
    1.22
     również
    1.17
     monies
    1.16
     IMHO
    1.08
     opět
    1.05
     mempunyai
    1.04
     spowod
    1.02
     verzorg
    0.99
    IMHO
    0.99
     stated
    0.98
    Activations Density 0.193%

    No Known Activations