© 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. 71846
    Prev
    Next
    INDEX
    Explanations

    waste, pollution, meaning

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

    fix the grammar

    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
    wikidata
    0.47
    栲
    0.46
    ниць
    0.44
     обслуживания
    0.44
    ಾರಂಭ
    0.43
    ణి
    0.43
    保有
    0.43
     ваших
    0.43
    кові
    0.43
    falfa
    0.43
    POSITIVE LOGITS
     Team
    0.48
     }^{
    0.45
     Fever
    0.45
     hatten
    0.44
     Club
    0.44
     Cake
    0.43
     Funeral
    0.42
     File
    0.41
     Project
    0.41
     Property
    0.41
    Activations Density 0.000%

    No Known Activations