© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1967
    Prev
    Next
    INDEX
    Explanations

    billions of parameters

    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_40_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
     mexico
    0.40
     প্রতিরোধের
    0.39
    communic
    0.39
     contributo
    0.39
     perspici
    0.38
    高級
    0.38
     प्रजनन
    0.38
    ॔
    0.38
    शिंग
    0.38
     христиан
    0.37
    POSITIVE LOGITS
     parameter
    0.94
     Parameter
    0.84
    parameter
    0.83
    Parameter
    0.76
    パラメータ
    0.71
    Parameters
    0.71
    参数
    0.71
     parameters
    0.69
     Parameters
    0.68
     size
    0.67
    Activations Density 0.023%

    No Known Activations