© 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. 44918
    Prev
    Next
    INDEX
    Explanations

    personal and government contexts

    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
     is
    -2.23
    ↵
    -2.09
     autre
    -1.59
     He
    -1.51
     you
    -1.51
    这几
    -1.48
    </b>
    -1.48
     :
    -1.47
     Which
    -1.47
    到现在
    -1.46
    POSITIVE LOGITS
     such
    1.85
    쫀
    1.84
     gmina
    1.77
    registrer
    1.65
    Опис
    1.57
    一身
    1.56
    Such
    1.55
    ʘ
    1.55
    𝘠
    1.53
    zzlement
    1.52
    Activations Density 0.002%

    No Known Activations