© 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. 29994
    Prev
    Next
    INDEX
    Explanations

    speciality, nationality, identity

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

    identifying different types or quantities

    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
    夏季
    0.44
    수를
    0.43
    蠵
    0.42
    वक
    0.41
     셀
    0.41
    ều
    0.40
     টেব
    0.40
     찍
    0.40
    キット
    0.40
    지요
    0.39
    POSITIVE LOGITS
    чит
    0.47
     nationality
    0.45
     upbringing
    0.44
     speciality
    0.44
     paix
    0.43
     participación
    0.43
     positivity
    0.42
     प्रोत्साहन
    0.42
     troupes
    0.42
    IdentityProvider
    0.42
    Activations Density 0.000%

    No Known Activations