© 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. 51982
    Prev
    Next
    INDEX
    Explanations

    how something is used responsibly

    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
     ਗ
    0.44
     свидетель
    0.44
     travaux
    0.42
     Gasp
    0.41
    ੯
    0.41
    Examination
    0.40
     Comte
    0.40
     আন্ত
    0.39
    >∑</
    0.39
    ລາ
    0.39
    POSITIVE LOGITS
    ణు
    0.38
    看不
    0.38
     import
    0.37
     honest
    0.37
    chars
    0.36
    Можно
    0.36
    齐
    0.36
     anatomical
    0.35
     send
    0.35
    require
    0.35
    Activations Density 0.005%

    No Known Activations