© 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. 56278
    Prev
    Next
    INDEX
    Explanations

    meta description, comprehensive plan

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

    **Patient Name:** label

    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
     offici
    0.47
    梅
    0.47
    bung
    0.47
    泂
    0.46
    f
    0.46
    主人
    0.45
    gf
    0.45
    chung
    0.44
    ol
    0.44
    情的
    0.44
    POSITIVE LOGITS
     downloading
    0.51
     가운데
    0.50
     decentralized
    0.48
     defaulted
    0.47
     केवल
    0.46
    )=
    0.46
     가장
    0.46
    ).
    0.45
     canceling
    0.45
     securing
    0.45
    Activations Density 0.000%

    No Known Activations