© 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. 2369
    Prev
    Next
    INDEX
    Explanations

    Python try: block

    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
     Ι
    0.78
    ные
    0.75
    are
    0.75
     aphids
    0.72
     Х
    0.72
    imately
    0.70
     И
    0.69
     theſe
    0.69
    chées
    0.69
    <unused682>
    0.69
    POSITIVE LOGITS
    ك
    1.02
    ف
    1.00
    7
    0.97
    ה
    0.96
    ס
    0.95
    지
    0.92
    6
    0.91
    c
    0.91
    8
    0.88
    на
    0.87
    Activations Density 0.473%

    No Known Activations