© 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. 71590
    Prev
    Next
    INDEX
    Explanations

    quoted phrases

    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
     pagină
    -1.39
    ⢅
    -1.38
     However
    -1.37
    區域
    -1.34
    りたい
    -1.31
     It
    -1.31
    titi
    -1.30
    ujesz
    -1.29
     decât
    -1.28
    を開催
    -1.28
    POSITIVE LOGITS
     of
    1.72
     dritte
    1.52
     podían
    1.31
    需要
    1.30
    camisa
    1.27
    ранее
    1.26
     pudieron
    1.26
    psfrag
    1.23
    НЫ
    1.22
    茘
    1.22
    Activations Density 0.093%

    No Known Activations