© 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. 10-GEMMASCOPE-RES-131K
    7. 40136
    Prev
    Next
    INDEX
    Explanations

    knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    壜
    -1.96
    神器
    -1.84
    垵
    -1.84
    隄
    -1.83
    '
    -1.83
    𓄹
    -1.81
     problém
    -1.77
    इटम
    -1.76
    鼉
    -1.76
    提现
    -1.74
    POSITIVE LOGITS
    .
    2.27
     of
    2.20
    而
    2.17
     about
    2.13
    但是
    2.00
     regiões
    1.91
     stattfinden
    1.88
    0
    1.88
     Bewußt
    1.88
     But
    1.84
    Activations Density 0.035%

    No Known Activations