© 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. 141218
    Prev
    Next
    INDEX
    Explanations

    LLC, alternative, juice, save, for the

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

    reusable logic, services, update

    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
    religion
    0.49
    رسٹ
    0.49
    sores
    0.46
    ready
    0.46
    窕
    0.45
    hmen
    0.45
    Religion
    0.44
    religious
    0.44
     religion
    0.44
    oramic
    0.44
    POSITIVE LOGITS
     частью
    0.52
     také
    0.52
     এটাও
    0.50
     duž
    0.46
     ankaŭ
    0.46
    ,<
    0.46
     tudi
    0.45
     también
    0.45
     boldly
    0.45
     интегри
    0.45
    Activations Density 0.000%

    No Known Activations