© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220668
    Prev
    Next
    INDEX
    Explanations

    INSTALLED_APPS configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    靜
    0.40
     {
    0.39
    ຄ
    0.39
    വന
    0.39
    ौरी
    0.39
    жд
    0.38
     প
    0.38
    ([[
    0.37
    ters
    0.37
     ಭ
    0.37
    POSITIVE LOGITS
     Installed
    0.55
    installed
    0.52
     installed
    0.51
    Installed
    0.51
     instalado
    0.46
    getInstalled
    0.42
     installé
    0.41
     installieren
    0.40
    amano
    0.39
     رباع
    0.39
    Activations Density 0.001%

    No Known Activations