© 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. 69405
    Prev
    Next
    INDEX
    Explanations

    past events

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

    readable and insightful

    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
    트
    0.58
    INFIN
    0.47
    ତ
    0.46
    함으로써
    0.44
    宣告
    0.43
    G
    0.43
    Α
    0.43
    扶
    0.43
    ათ
    0.43
    H
    0.42
    POSITIVE LOGITS
     istor
    0.47
     Talk
    0.46
     الكلام
    0.46
     seeded
    0.45
     Beberapa
    0.45
     Quality
    0.45
     Monitor
    0.45
     talked
    0.44
     atau
    0.43
     মিটিং
    0.43
    Activations Density 0.000%

    No Known Activations