© 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-16K
    7. 12636
    Prev
    Next
    INDEX
    Explanations

    programming file paths

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

    namespace followed by context names

    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_16k_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
    ؛
    0.55
    ،
    0.50
     పరిస్థ
    0.49
     لباس
    0.48
     والله
    0.48
     مختلفة
    0.48
    ленд
    0.48
     مستقبل
    0.48
     وجه
    0.46
     personen
    0.45
    POSITIVE LOGITS
    Ve
    0.40
    ASP
    0.40
    cB
    0.40
    xB
    0.39
    iD
    0.38
    厶
    0.38
    []){
    0.38
    SPs
    0.38
    exion
    0.38
     Outstanding
    0.38
    Activations Density 0.000%

    No Known Activations