© 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. 216042
    Prev
    Next
    INDEX
    Explanations

    exploratory mining projects

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

    technical requirements and labels

    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
     handset
    0.53
     lawmaker
    0.49
    AH
    0.48
     অবস্থায়
    0.47
     settings
    0.47
     keras
    0.46
     employeeService
    0.46
     AJ
    0.46
     that
    0.45
     ذ
    0.45
    POSITIVE LOGITS
     Pore
    0.54
    ඩි
    0.50
    오는
    0.48
     equidistant
    0.43
     ترس
    0.42
    ки
    0.42
    ապ
    0.42
    kań
    0.42
    ographiques
    0.42
     पोर्ट
    0.41
    Activations Density 0.001%

    No Known Activations