© 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. 58613
    Prev
    Next
    INDEX
    Explanations

    Multilingual names and grammatical structures

    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
    an
    -2.66
    艫
    -2.41
     Gegensatz
    -2.41
     Hinblick
    -2.31
     чтобы
    -2.22
     vorigen
    -2.22
    桕
    -2.08
    駸
    -2.06
     turista
    -2.05
    ()),
    -2.02
    POSITIVE LOGITS
    {
    3.02
    2
    2.47
    5
    2.44
    1
    2.23
     भी
    2.20
    ड़
    2.17
    这么
    2.09
     bedeckt
    2.05
    那我
    2.02
     Ответить
    2.02
    Activations Density 0.000%

    No Known Activations