© 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. 255862
    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
    motionProxy
    0.49
    UOUS
    0.45
     CONSEQUENTIAL
    0.45
    ული
    0.44
    ➘
    0.43
    Missense
    0.43
    खिक
    0.43
    ктери
    0.42
    ϓ
    0.42
    κρι
    0.41
    POSITIVE LOGITS
     आश्वासन
    0.56
     lot
    0.50
    ão
    0.49
    lot
    0.49
     właści
    0.48
     Abhäng
    0.48
     instituição
    0.48
    ửa
    0.48
    iting
    0.47
     場
    0.47
    Activations Density 0.000%

    No Known Activations