© 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. 34-GEMMASCOPE-RES-131K
    7. 57681
    Prev
    Next
    INDEX
    Explanations

    business and finance contexts

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

    The neuron is tracking token position, with activation rising as you move further into a document.

    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
    储存
    -1.30
     yalnızca
    -1.22
    ค่ะ
    -1.19
     zuständig
    -1.18
    romyalgia
    -1.16
     ทาง
    -1.09
    猛地
    -1.09
    𝕒
    -1.09
    ßten
    -1.09
     envision
    -1.08
    POSITIVE LOGITS
     Whilst
    1.83
    Whilst
    1.73
     whilst
    1.59
     circa
    1.40
     Notwithstanding
    1.09
    iriman
    1.09
    CascadeType
    1.09
    蹂
    1.02
     nirvana
    1.01
    米国
    1.00
    Activations Density 0.132%

    No Known Activations