© 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. 16-GEMMASCOPE-2-RES-262K
    7. 35448
    Prev
    Next
    INDEX
    Explanations

    csv files and tables

    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_16_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
     MOU
    0.88
    ৫
    0.84
    数据
    0.84
     clamps
    0.79
    ה
    0.79
     oznac
    0.78
     commandments
    0.77
     μιας
    0.77
    ;//
    0.77
     AMC
    0.77
    POSITIVE LOGITS
    at
    1.13
    l
    1.09
    r
    1.05
    il
    0.98
    s
    0.96
    d
    0.96
    os
    0.95
    ar
    0.94
    elser
    0.93
    ig
    0.93
    Activations Density 0.007%

    No Known Activations