© 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. 254633
    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
    ت
    0.59
    ي
    0.53
    преде
    0.47
    正
    0.46
    <0xE3>
    0.46
    дро
    0.46
    эн
    0.45
    et
    0.45
    ช่วง
    0.44
    و
    0.44
    POSITIVE LOGITS
     miserable
    0.58
     ati
    0.55
     failings
    0.52
     penjualan
    0.52
     einfacher
    0.51
     injust
    0.51
     estoppel
    0.51
     accett
    0.50
     wäre
    0.50
     cutest
    0.50
    Activations Density 0.000%

    No Known Activations