© 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. 6577
    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
    0.51
    a
    0.50
     Kall
    0.49
     कस
    0.47
    depos
    0.47
    d
    0.47
     Stuck
    0.45
    Shoot
    0.44
     Popov
    0.44
    e
    0.44
    POSITIVE LOGITS
     engend
    0.57
    だと思います
    0.50
     fundamentos
    0.48
    ylmethylsulfanyl
    0.48
    と思いますが
    0.48
    とは思
    0.47
     ordinairement
    0.47
     überprü
    0.47
     取っ
    0.47
     QuantityOnHand
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.