© 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. 51924
    Prev
    Next
    INDEX
    Explanations

    social media post

    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
    ۲
    0.50
    २
    0.48
     ۲۰
    0.43
    の記事
    0.43
    article
    0.41
    фа
    0.41
     சேர்ந்த
    0.41
    dSample
    0.41
    െ
    0.41
    ५
    0.41
    POSITIVE LOGITS
     made
    0.63
    made
    0.51
     feitas
    0.47
     feito
    0.47
     asking
    0.46
     madeira
    0.46
     feitos
    0.46
     poro
    0.46
     செய்யப்பட்ட
    0.45
     сдела
    0.44
    Activations Density 0.018%

    No Known Activations