© 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. 259091
    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
    u
    0.55
     approval
    0.52
     dissected
    0.49
    рке
    0.49
     sighting
    0.48
     subgroup
    0.47
    im
    0.47
     construction
    0.47
     suppression
    0.47
     educator
    0.46
    POSITIVE LOGITS
     মহা
    0.58
     první
    0.51
     গিয়েছিল
    0.47
     velho
    0.46
    ၻ
    0.44
     neh
    0.44
    休日
    0.44
    ნიშვნელ
    0.44
    ဟုတ်
    0.43
     tradi
    0.43
    Activations Density 0.001%

    No Known Activations