© 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. 241536
    Prev
    Next
    INDEX
    Explanations

    international or foreign words

    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
    Mc
    0.54
    San
    0.53
    SAN
    0.51
    Ta
    0.51
    On
    0.49
    T
    0.49
    Emer
    0.48
    Club
    0.48
    ׳
    0.48
    Jour
    0.47
    POSITIVE LOGITS
     dolomite
    0.57
     डॉलर
    0.55
     봉
    0.53
    wakilan
    0.52
     보는
    0.51
    ங்களைப்
    0.51
     rupiah
    0.51
     sext
    0.50
     문제
    0.49
     bale
    0.49
    Activations Density 0.001%

    No Known Activations