© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143250
    Prev
    Next
    INDEX
    Explanations

    knowing context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يجب
    0.48
     estadounidense
    0.46
     Umsetzung
    0.46
    Э
    0.46
     versiones
    0.44
     giapp
    0.44
     више
    0.43
     створи
    0.43
     estadounidenses
    0.43
    栱
    0.43
    POSITIVE LOGITS
     but
    0.47
     extortion
    0.45
    nor
    0.45
    but
    0.45
     journalist
    0.45
    hta
    0.44
    agent
    0.43
     incentive
    0.43
     agents
    0.42
     mutta
    0.42
    Activations Density 0.002%

    No Known Activations