© 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. 119830
    Prev
    Next
    INDEX
    Explanations

    instructor, candidates

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

    domains and subjects

    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
    standing
    0.46
    ما
    0.45
     annealed
    0.44
    copies
    0.44
    </i>
    0.44
    ments
    0.43
    _
    0.43
    </h2>
    0.43
    matching
    0.42
     ㅁ
    0.42
    POSITIVE LOGITS
     descricao
    0.52
     hogi
    0.52
     giud
    0.48
     fomentar
    0.47
     dovrà
    0.47
     mogao
    0.47
    GEBURTS
    0.47
     nourrice
    0.47
     způsob
    0.46
     dakkh
    0.46
    Activations Density 0.001%

    No Known Activations