© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136491
    Prev
    Next
    INDEX
    Explanations

    years, anos, anni, vuos, days

    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_262k_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
     фундамента
    0.54
     подход
    0.52
    ranged
    0.48
    솔
    0.47
     оптима
    0.46
     потребности
    0.46
     вектор
    0.45
    }_{+}
    0.45
     порядок
    0.44
     दिव्य
    0.44
    POSITIVE LOGITS
     olim
    0.54
     years
    0.50
     anos
    0.49
     giorni
    0.49
     flores
    0.46
     vuos
    0.45
    8
    0.45
     anni
    0.44
     aast
    0.44
     hohen
    0.43
    Activations Density 0.003%

    No Known Activations