© 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. 206837
    Prev
    Next
    INDEX
    Explanations

    sell Iran

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

    realistic and reproducible

    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
    iz
    0.54
     notify
    0.53
    ة
    0.50
     (,
    0.49
     approve
    0.49
     accept
    0.49
     adjust
    0.48
     nominate
    0.48
     Accept
    0.47
     authorize
    0.46
    POSITIVE LOGITS
     кін
    0.51
     رکھے
    0.44
    ✙
    0.44
     NIN
    0.44
    ᓴ
    0.42
    บัน
    0.41
    ENSE
    0.41
    TRAN
    0.41
     kriy
    0.40
    ทรวง
    0.40
    Activations Density 0.001%

    No Known Activations