© 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. 100361
    Prev
    Next
    INDEX
    Explanations

    sync across

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

    polymorphism Allocation Formatting

    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
     keenly
    0.45
    ↷
    0.44
     onlookers
    0.44
     resistentes
    0.44
    spun
    0.44
     resisted
    0.44
     dukkham
    0.43
     considér
    0.43
    ou
    0.43
     resisting
    0.43
    POSITIVE LOGITS
     polymorphism
    0.46
    ナス
    0.45
    齧
    0.44
     Beans
    0.42
    NERVE
    0.42
    opcode
    0.42
     flakes
    0.42
    一大
    0.41
     net
    0.41
     Logistics
    0.41
    Activations Density 0.000%

    No Known Activations