© 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-65K
    7. 2450
    Prev
    Next
    INDEX
    Explanations

    superscript numbers

    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_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
    מ
    1.37
    т
    1.16
    ב
    1.15
    ت
    1.14
    о
    0.99
    اي
    0.94
    ди
    0.94
    ات
    0.89
    ных
    0.88
    は
    0.88
    POSITIVE LOGITS
    att
    0.84
    ’
    0.70
    in
    0.67
    ine
    0.62
    ra
    0.61
    ired
    0.60
    ls
    0.60
    CY
    0.59
    DA
    0.57
     "")
    0.56
    Activations Density 0.172%

    No Known Activations