© 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. 204022
    Prev
    Next
    INDEX
    Explanations

    authentic football jersey

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

    cultural differences and specific meaning

    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
    ত
    0.54
    Thời
    0.54
     Thời
    0.54
    lekt
    0.53
    okok
    0.53
    setDefault
    0.51
    הר
    0.50
    al
    0.50
    ंपूर्
    0.50
    鸥
    0.50
    POSITIVE LOGITS
     colloidal
    0.45
     vendido
    0.45
     অধিদপ্তর
    0.44
     vendidos
    0.44
     colis
    0.44
     coordinates
    0.43
     plaint
    0.43
     destac
    0.42
     sickly
    0.42
     moieties
    0.42
    Activations Density 0.002%

    No Known Activations