© 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-262K
    7. 163860
    Prev
    Next
    INDEX
    Explanations

    Islamists, ancient palace

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

    cinematic lighting and composition

    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_262k_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
     Woh
    0.48
    usste
    0.48
     Honorable
    0.46
     overwhelmingly
    0.45
    ЭС
    0.45
    teo
    0.45
    носит
    0.44
     Ш
    0.44
     Sule
    0.43
     உருவாக்கு
    0.42
    POSITIVE LOGITS
    łka
    0.53
    चल
    0.51
     seharusnya
    0.49
    actin
    0.48
    सामान्यीकृत
    0.47
    दूस
    0.47
    चाल
    0.46
    >∕
    0.46
     shooters
    0.46
     kinases
    0.46
    Activations Density 0.001%

    No Known Activations