© 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. 252231
    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
     shells
    0.54
     catches
    0.50
    出荷
    0.48
     empty
    0.48
     CH
    0.47
     mid
    0.47
     G
    0.47
     auditors
    0.47
     municipales
    0.47
     mill
    0.46
    POSITIVE LOGITS
    ēt
    0.53
    Salir
    0.50
    ēm
    0.50
    Camp
    0.49
    𝒄
    0.49
    hydraz
    0.49
    sez
    0.48
    σης
    0.48
    sama
    0.48
    ōs
    0.48
    Activations Density 0.000%

    No Known Activations