© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34534
    Prev
    Next
    INDEX
    Explanations

    conditional descriptions across languages

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

    The neuron fires on dense technical or mathematical jargon—particularly advanced quantitative and modeling terminology you’d find in academic research abstracts.

    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
     テーブル
    -1.20
    .
    -1.16
    かは
    -1.13
     indef
    -1.12
     nachher
    -1.11
     endroits
    -1.08
    额头
    -1.08
    吏
    -1.07
     Parcel
    -1.07
     anschließend
    -1.06
    POSITIVE LOGITS
    ֝
    1.62
    ֭
    1.50
    Beskrivning
    1.50
    توضیحات
    1.48
    ֠
    1.42
    Vaata
    1.41
    әһ
    1.41
     mendatang
    1.40
    dération
    1.39
    Beskrivelse
    1.37
    Activations Density 0.708%

    No Known Activations