© 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. 63496
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by noun/adjective

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

    events and states

    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
     silicon
    0.40
    ഞ്ഞി
    0.38
     diffère
    0.38
     πολύ
    0.38
     Calvert
    0.37
     referred
    0.36
     poignant
    0.36
     cypress
    0.36
     westerly
    0.36
    ǁ
    0.35
    POSITIVE LOGITS
     이제
    0.47
    이제
    0.44
     말미암
    0.40
    のために
    0.40
     ذریعے
    0.39
     kanggo
    0.39
     skulle
    0.38
    აქ
    0.38
     본격
    0.38
    ัติ
    0.37
    Activations Density 0.000%

    No Known Activations