© 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. 226756
    Prev
    Next
    INDEX
    Explanations

    new or clean

    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
    net
    0.48
    NET
    0.46
    🧂
    0.46
    ตอน
    0.44
    這一
    0.44
     joie
    0.43
    損
    0.43
    岡山
    0.42
    銨
    0.42
    bankruptcy
    0.42
    POSITIVE LOGITS
     Clase
    0.42
    ரை
    0.41
     Togo
    0.41
    rbrakk
    0.41
     sleeveless
    0.41
    স্থল
    0.41
     Sailors
    0.40
    zare
    0.40
     País
    0.40
    ird
    0.40
    Activations Density 0.000%

    No Known Activations