© 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. 77898
    Prev
    Next
    INDEX
    Explanations

    links and titles

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

    simulating human traits

    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
    Not in Any Lists

    No Comments

    Negative Logits
    षेक
    0.45
    ώσεις
    0.43
    ίου
    0.43
    胚
    0.43
    ौला
    0.41
    Put
    0.41
    ীকে
    0.41
    提名
    0.40
    狍
    0.40
    lení
    0.40
    POSITIVE LOGITS
     kanssa
    0.51
     orchestra
    0.47
     allong
    0.46
     diffract
    0.46
     flow
    0.45
     acon
    0.45
     كمان
    0.45
     engineer
    0.45
     таксама
    0.45
     kuliah
    0.45
    Activations Density 0.001%

    No Known Activations