© 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. 256949
    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
     čís
    0.43
     -
    0.43
     دى
    0.42
     كرة
    0.42
    riers
    0.42
     في
    0.41
    י
    0.40
    ν
    0.40
     .
    0.40
     τέ
    0.40
    POSITIVE LOGITS
     प्लॉट
    0.51
     whopping
    0.46
     entered
    0.46
     penilaian
    0.45
    ມັນ
    0.45
    நக
    0.44
    adiq
    0.44
     peristiwa
    0.43
     નવા
    0.43
     impresionante
    0.42
    Activations Density 0.001%

    No Known Activations