© 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. 40406
    Prev
    Next
    INDEX
    Explanations

    years

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

    year 2024

    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
     ၂
    0.48
     त्यावेळी
    0.47
     senere
    0.47
     trouvait
    0.46
     사고
    0.46
     Qxa
    0.46
     সোভিয়েত
    0.46
    日子
    0.46
     murderer
    0.45
     당시
    0.45
    POSITIVE LOGITS
     are
    0.64
    ן
    0.54
    ные
    0.51
    ée
    0.50
    ुत
    0.49
    ête
    0.48
    ↵↵
    0.48
    ′
    0.48
     serán
    0.48
     will
    0.47
    Activations Density 0.068%

    No Known Activations