© 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. 228846
    Prev
    Next
    INDEX
    Explanations

    selenium reducing inflammation

    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
    τουργ
    0.45
     Polytechnic
    0.45
     Medicinal
    0.44
    ੩
    0.43
     Horticulture
    0.43
     NUR
    0.42
    wór
    0.42
     এদের
    0.42
     bij
    0.41
     hort
    0.41
    POSITIVE LOGITS
    OMG
    0.45
     sigur
    0.45
     กลับ
    0.44
    GAME
    0.42
     เข
    0.41
     🔥
    0.41
     datth
    0.41
    デー
    0.40
    🔥
    0.39
    checking
    0.39
    Activations Density 0.003%

    No Known Activations