© 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. 22-GEMMASCOPE-RES-131K
    7. 104242
    Prev
    Next
    INDEX
    Explanations

    needs or wants

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

    The neuron strongly activates on multi‐syllable, domain-specific content words (technical nouns and jargon).

    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
     or
    -1.03
     any
    -0.93
     first
    -0.93
     prevent
    -0.89
    Before
    -0.88
     megfelelő
    -0.87
     every
    -0.86
    生態
    -0.85
    Other
    -0.85
    arrivo
    -0.85
    POSITIVE LOGITS
     needed
    1.34
     needing
    1.24
     wanting
    1.15
    ต้องการ
    1.14
    needed
    1.14
    需要
    1.13
     cần
    1.09
     needs
    1.09
     besoin
    1.09
     besoins
    1.04
    Activations Density 0.297%

    No Known Activations