© 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. 176413
    Prev
    Next
    INDEX
    Explanations

    into breast milk

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

    describing typical behaviors and states

    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
     অনুসরণ
    0.54
    לך
    0.52
    MORDOR
    0.52
     Tiet
    0.51
     sigue
    0.50
    ３
    0.50
     பின்பற்ற
    0.50
    スタンダード
    0.50
    やっぱり
    0.50
    ╡
    0.49
    POSITIVE LOGITS
     engagements
    0.45
     maternity
    0.43
     compilation
    0.42
     “(
    0.41
     livelihood
    0.41
     governance
    0.41
     eng
    0.40
    ্যো
    0.40
     compiling
    0.40
     mij
    0.38
    Activations Density 0.000%

    No Known Activations