© 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. 126041
    Prev
    Next
    INDEX
    Explanations

    foreign and domestic policy

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

    pointers, memory, risks, cities

    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
    gz
    0.50
    の手
    0.48
     소
    0.46
    outline
    0.46
    outfile
    0.46
    oz
    0.44
     çı
    0.44
    ຝ
    0.44
    อิ
    0.43
    fname
    0.43
    POSITIVE LOGITS
    алет
    0.52
     delightful
    0.48
     Commanders
    0.47
     Staats
    0.44
     Residents
    0.44
     Missions
    0.44
     invites
    0.44
    بعد
    0.44
     Spirits
    0.44
     Waits
    0.44
    Activations Density 0.001%

    No Known Activations