© 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. 9772
    Prev
    Next
    INDEX
    Explanations

    if you

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

    if you are experiencing

    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
     एखा
    0.42
    :"",
    0.34
    Radiux
    0.32
    Container
    0.32
    issuer
    0.32
    oidal
    0.32
    Generating
    0.30
     vouloir
    0.30
    উদাহরণ
    0.30
    :'',
    0.30
    POSITIVE LOGITS
     البطولة
    0.35
     Kijk
    0.33
    යි
    0.33
    tem
    0.32
     Nog
    0.32
     juge
    0.32
     দিয়েছে
    0.32
    มัน
    0.32
    راه
    0.32
    riches
    0.32
    Activations Density 0.062%

    No Known Activations