© 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. 165242
    Prev
    Next
    INDEX
    Explanations

    describing subsequent entities

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

    fantasies with harmful implications

    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
     Шта
    0.45
    ன்
    0.44
    тива
    0.43
    தொ
    0.43
     организация
    0.42
     Sick
    0.42
    Д
    0.41
     Kao
    0.41
     troops
    0.41
     stepped
    0.41
    POSITIVE LOGITS
     transfer
    0.53
    az
    0.52
    transfer
    0.45
    ገድ
    0.45
     果
    0.45
    ctxt
    0.44
     المشروع
    0.44
     korero
    0.43
     பேராசிரியர்
    0.43
    thai
    0.43
    Activations Density 0.001%

    No Known Activations