© 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-65K
    7. 28507
    Prev
    Next
    INDEX
    Explanations

    workout plan for a week

    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_65k_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
    ℃
    0.48
     DENUMIRE
    0.47
    b
    0.46
    gir
    0.46
     rå
    0.45
    fired
    0.45
    bear
    0.45
    gat
    0.44
    fixed
    0.43
    etah
    0.43
    POSITIVE LOGITS
     normales
    0.51
     especies
    0.47
     une
    0.47
     не
    0.47
     Poli
    0.46
    ຂໍ
    0.45
    ە
    0.45
     ün
    0.45
     individuales
    0.45
     exemplos
    0.44
    Activations Density 0.008%

    No Known Activations