© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25764
    Prev
    Next
    INDEX
    Explanations

    life, death, and change

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

    philosophical or poetic statements about life, death, or love.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on abstract, introspective terms—words about life, change, self, and existential questions.

    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
     >
    -1.22
    וּ
    -1.15
     đang
    -1.15
    !
    -1.09
    :
    -1.07
     now
    -1.05
     will
    -1.05
    娱
    -1.03
    >
    -1.03
     المزيد
    -1.03
    POSITIVE LOGITS
     certaines
    1.46
     ανθρώ
    1.40
     certain
    1.40
     someone
    1.34
     sometimes
    1.34
    𝐽
    1.29
     někter
    1.27
     člověk
    1.26
     ciertas
    1.24
     people
    1.23
    Activations Density 0.067%

    No Known Activations