© 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. 10-GEMMASCOPE-RES-131K
    7. 99753
    Prev
    Next
    INDEX
    Explanations

    paternal and maternal lineage

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

    familial relationships in genealogical or biographical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     in
    -1.40
    élie
    -1.23
    自己的
    -1.20
     confirmó
    -1.17
    𓆟
    -1.16
     outcomes
    -1.14
    bihi
    -1.13
     ketahui
    -1.09
     desarrollan
    -1.09
     developments
    -1.07
    POSITIVE LOGITS
    sider
    1.26
     รถ
    1.26
    걍
    1.26
     Uniwers
    1.25
    ⚀
    1.22
    álu
    1.20
    りましたが
    1.20
    jordan
    1.20
     flink
    1.20
    árol
    1.19
    Activations Density 0.032%

    No Known Activations