© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 141502
    Prev
    Next
    INDEX
    Explanations

    suburb and woman

    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
    ни
    0.55
    حافظ
    0.47
    AI
    0.47
     Bolet
    0.47
    зирован
    0.46
     loophole
    0.46
    였
    0.45
    も
    0.44
    лет
    0.44
    栞
    0.42
    POSITIVE LOGITS
    ında
    0.57
    al
    0.56
    onga
    0.55
    alles
    0.54
    ğun
    0.54
    ća
    0.54
    odzi
    0.53
    hamton
    0.53
    pus
    0.52
    খাস্ত
    0.52
    Activations Density 0.001%

    No Known Activations