© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 96589
    Prev
    Next
    INDEX
    Explanations

    where or referring

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

    where or wherein

    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
    ण्याचा
    0.40
    ActionResult
    0.38
    думы
    0.37
    હ
    0.37
     শুধ
    0.37
     सोच
    0.37
    otland
    0.37
    rpart
    0.36
    प्रभाव
    0.36
     옷
    0.36
    POSITIVE LOGITS
     where
    0.75
     где
    0.68
     referring
    0.67
     wherein
    0.66
     όπου
    0.66
     dimana
    0.64
     gdzie
    0.63
     যেখানে
    0.62
     donde
    0.61
     Where
    0.61
    Activations Density 0.025%

    No Known Activations