© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11729
    Prev
    Next
    INDEX
    Explanations

    visit the web-site

    np_acts-logits-general · gemini-2.5-flash-lite

    focusing on effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arXiv
    0.49
    Images
    0.49
     Wallpaper
    0.47
    蒎
    0.47
    OMe
    0.47
    ീപ
    0.46
    OWL
    0.46
    ILI
    0.46
     Vào
    0.46
    Workshop
    0.45
    POSITIVE LOGITS
     complacent
    0.48
     appointing
    0.47
    거
    0.45
    र्ग
    0.45
     solucion
    0.45
    hent
    0.45
    ]['
    0.44
     lanjutan
    0.43
     cara
    0.42
     telecoms
    0.42
    Activations Density 0.008%

    No Known Activations