© 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. 252223
    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
    פ
    0.48
     dependant
    0.48
     flancs
    0.48
     abortions
    0.48
    ಿದ್ದೇವೆ
    0.46
     defaulting
    0.46
    礎
    0.45
    ಡೆ
    0.45
     REACTORS
    0.44
     треба
    0.44
    POSITIVE LOGITS
     is
    0.48
     Irwin
    0.46
     Marconi
    0.45
    速
    0.44
     Sarah
    0.43
     LZ
    0.43
     inspect
    0.43
     Higgins
    0.43
     agave
    0.43
     Jenna
    0.43
    Activations Density 0.001%

    No Known Activations