© 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. 71097
    Prev
    Next
    INDEX
    Explanations

    configuration and code snippets

    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
     checkbox
    0.47
     checkboxes
    0.47
    </h3>
    0.45
     workaround
    0.44
     cập
    0.43
     มัน
    0.42
    探测
    0.40
    checkbox
    0.40
    籀
    0.40
    ографи
    0.40
    POSITIVE LOGITS
     اسمه
    0.54
     اسمها
    0.53
    悠
    0.46
    েষ
    0.44
     אותו
    0.44
    merksam
    0.44
     vertebrae
    0.43
    selfish
    0.43
     имя
    0.43
     इंपोर्टेंट
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.