© 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. 178519
    Prev
    Next
    INDEX
    Explanations

    work, efforts, icons, potential, shifts, paid, board

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

    uncertainty, surprise, achievements, inquiry

    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
     Bil
    0.51
     it
    0.49
    茸
    0.47
     Okan
    0.47
    PRE
    0.46
    O
    0.46
     oud
    0.45
     Ven
    0.45
     aki
    0.45
     عمان
    0.45
    POSITIVE LOGITS
     ثلاث
    0.49
    istra
    0.48
     ಪುಸ್ತಕ
    0.48
    ist
    0.47
    otesi
    0.46
     ત્રણ
    0.46
    抂
    0.45
     книгу
    0.45
    spicuous
    0.44
    规
    0.44
    Activations Density 0.000%

    No Known Activations