© 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. 108096
    Prev
    Next
    INDEX
    Explanations

    academic and professional backgrounds

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

    degree requirements

    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
    டிக்க
    0.40
    конец
    0.38
     oprav
    0.38
     जख
    0.38
     educación
    0.37
    DIVISION
    0.36
     educativo
    0.36
     ख
    0.35
    ெடு
    0.35
     éduc
    0.35
    POSITIVE LOGITS
     afterwards
    0.45
     afterward
    0.43
     χρώ
    0.43
     Theoretical
    0.43
     theoretical
    0.42
     সন্তানের
    0.42
     potem
    0.41
    theoretical
    0.41
    thorpe
    0.40
     पढ़ाने
    0.40
    Activations Density 0.080%

    No Known Activations