© 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. 216580
    Prev
    Next
    INDEX
    Explanations

    buildings and products

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

    physical structures or statuses

    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
    䐍
    0.45
     pars
    0.44
    谨慎
    0.44
    ่า
    0.44
    ✽
    0.44
    ิบ
    0.43
    פר
    0.43
    ❥
    0.43
     nỗi
    0.43
    miş
    0.43
    POSITIVE LOGITS
     يعد
    0.48
     registro
    0.47
     registers
    0.47
    ্ক
    0.46
     κατά
    0.45
    sk
    0.45
     proportionality
    0.45
     zwischen
    0.45
     spune
    0.45
     znamen
    0.44
    Activations Density 0.000%

    No Known Activations