© 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. 40-GEMMASCOPE-2-RES-65K
    7. 50763
    Prev
    Next
    INDEX
    Explanations

    Billy followed by names or objects

    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_40_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
     duckys
    0.42
     했
    0.38
     समस्याएं
    0.38
     সম্ভবত
    0.38
     తయ
    0.38
    揆
    0.38
    __);
    0.37
     creases
    0.37
    acaks
    0.37
    姬
    0.36
    POSITIVE LOGITS
     goat
    0.46
     Goat
    0.44
    goat
    0.44
    ede
    0.41
    ingu
    0.41
    ographical
    0.41
    pir
    0.40
     निम्नलिखित
    0.39
     काली
    0.39
    Joel
    0.39
    Activations Density 0.003%

    No Known Activations