© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108720
    Prev
    Next
    INDEX
    Explanations

    birth doula

    np_acts-logits-general · gemini-2.5-flash-lite

    moral and ethical concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     غ
    0.49
     CODE
    0.48
     Promo
    0.47
     أنا
    0.47
     те
    0.46
     интере
    0.46
     تون
    0.46
     זה
    0.45
    这也
    0.44
    多
    0.44
    POSITIVE LOGITS
    DialogInterface
    0.50
    \%).
    0.50
     বৎসরের
    0.50
     ออนไลน์
    0.49
    hetam
    0.47
    GBuf
    0.46
     製
    0.46
    ranges
    0.46
     剤
    0.46
    estimating
    0.46
    Activations Density 0.001%

    No Known Activations