© 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. 69571
    Prev
    Next
    INDEX
    Explanations

    intervention or meddling

    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
     laikā
    -1.20
     daudz
    -1.17
     cũng
    -1.16
    tifie
    -1.16
     Produit
    -1.14
     who
    -1.12
     urme
    -1.12
    '
    -1.09
    łeś
    -1.09
     employed
    -1.09
    POSITIVE LOGITS
    rões
    1.30
    CHREIB
    1.18
     in
    1.18
    tas
    1.14
    raeli
    1.14
    obut
    1.13
    作为一个
    1.12
    ⸨
    1.11
     日本の
    1.11
    zegor
    1.10
    Activations Density 0.050%

    No Known Activations