© 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. 44770
    Prev
    Next
    INDEX
    Explanations

    suddenly, accident, conflict

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

    recently launched

    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
     evocative
    0.47
    หรือ
    0.47
     spraw
    0.46
    จัก
    0.46
    ért
    0.45
    땐
    0.45
     infrastructure
    0.45
     parfois
    0.45
     infrast
    0.45
     trás
    0.45
    POSITIVE LOGITS
     বলল
    0.62
     Suddenly
    0.54
     അയാൾ
    0.53
     salesperson
    0.48
     suddenly
    0.48
    下列
    0.47
     বললো
    0.47
    ____
    0.46
     그런데
    0.46
     Однако
    0.46
    Activations Density 0.097%

    No Known Activations