© 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. 40022
    Prev
    Next
    INDEX
    Explanations

    good vs evil commandments

    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
     this
    -1.47
    ulisan
    -1.35
    after
    -1.19
    瀬戸
    -1.17
     døde
    -1.13
    Ана
    -1.12
    淥
    -1.11
     Sua
    -1.10
    ⁧
    -1.09
     記事
    -1.09
    POSITIVE LOGITS
    tabular
    1.36
     I
    1.29
     например
    1.25
    er
    1.21
     своим
    1.20
     chré
    1.18
    não
    1.17
    ੀ
    1.17
     alguna
    1.15
    ziasztok
    1.14
    Activations Density 0.012%

    No Known Activations