© 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. 71082
    Prev
    Next
    INDEX
    Explanations

    replacement for items or parts

    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
    蕯
    -2.83
     geladen
    -2.64
     bilde
    -2.56
    仅
    -2.56
    是
    -2.47
    {
    -2.45
    子的
    -2.41
     There
    -2.38
    Tentang
    -2.34
    Suka
    -2.34
    POSITIVE LOGITS
    姈
    3.48
     of
    3.38
    ↵
    3.28
    沨
    3.13
    酲
    2.98
    尨
    2.89
    媗
    2.84
    नलोड
    2.75
     is
    2.64
    迓
    2.64
    Activations Density 0.008%

    No Known Activations