© 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. 62063
    Prev
    Next
    INDEX
    Explanations

    logical path

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

    scientific or abstract concepts

    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
    细节
    0.49
    🦵
    0.47
    照顾
    0.47
     বাড়তি
    0.47
     আকর্ষণ
    0.46
     याता
    0.44
     আশে
    0.44
    ги
    0.44
     особенности
    0.43
     ব্যথা
    0.43
    POSITIVE LOGITS
     diá
    0.50
     smlou
    0.49
     sociedade
    0.48
    )}^{
    0.45
    LOCK
    0.45
     repub
    0.45
     diccionario
    0.45
     sociedades
    0.44
     debate
    0.43
     shar
    0.43
    Activations Density 0.000%

    No Known Activations