© 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. 260589
    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
     inklusive
    0.53
    atrical
    0.46
    volving
    0.45
    ០
    0.45
    af
    0.44
    akel
    0.44
     verdi
    0.44
    ſſ
    0.44
    yds
    0.44
    hko
    0.43
    POSITIVE LOGITS
     ansi
    0.46
    잖
    0.45
    GitHub
    0.43
    FUTURE
    0.43
    开源
    0.43
    临
    0.43
    לי
    0.43
    샌
    0.43
    してしまう
    0.42
     dispositivos
    0.42
    Activations Density 0.000%

    No Known Activations