© 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. 258973
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ugia
    0.53
    እንደ
    0.51
    ând
    0.47
    rna
    0.45
    overall
    0.45
    unable
    0.44
    nick
    0.44
    t
    0.43
    song
    0.43
    ताल
    0.42
    POSITIVE LOGITS
     besteht
    0.50
     bevor
    0.49
     beige
    0.47
     คณิตศาสตร์
    0.46
     bevat
    0.46
     بيانات
    0.46
     juz
    0.46
     winkel
    0.45
     labyr
    0.44
     regler
    0.44
    Activations Density 0.000%

    No Known Activations