© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 44807
    Prev
    Next
    INDEX
    Explanations

    biscuit or biscuits

    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
    ب
    0.54
    们
    0.49
     प्रशिक्षण
    0.48
    scaping
    0.48
     দর্শন
    0.47
    aining
    0.47
     त्रि
    0.46
     निरीक्षण
    0.45
    lemek
    0.44
    ophilic
    0.44
    POSITIVE LOGITS
    р
    0.52
    า
    0.52
     pov
    0.50
     Aynı
    0.50
     """"
    0.49
     aqui
    0.48
     "__
    0.47
    ר
    0.47
    linhas
    0.47
     преди
    0.47
    Activations Density 0.000%

    No Known Activations