© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127608
    Prev
    Next
    INDEX
    Explanations

    billed as images

    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
    ↵
    -4.09
     /
    -2.59
     indescri
    -2.52
    Лечение
    -2.50
    涣
    -2.33
    ции
    -2.25
    ～　
    -2.19
    ୌ
    -2.17
    bbean
    -2.13
    独特
    -2.13
    POSITIVE LOGITS
     quadrinhos
    3.06
    羕
    3.05
    皷
    2.81
    ㈬
    2.59
    甞
    2.55
    渽
    2.55
    赑
    2.55
    扨
    2.52
    薆
    2.52
     cittadino
    2.44
    Activations Density 0.002%

    No Known Activations