© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 255632
    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
     anticancer
    0.47
     आयुष
    0.43
    ţ
    0.43
    yilda
    0.42
     trav
    0.41
     اپنی
    0.41
    ay
    0.41
    jose
    0.41
     Yose
    0.41
     José
    0.41
    POSITIVE LOGITS
    Colleg
    0.48
     ноги
    0.45
     CED
    0.44
    堌
    0.43
     அரை
    0.42
    Comparer
    0.42
    𝐸
    0.41
    CED
    0.41
    Acknowledgment
    0.40
    রেক
    0.40
    Activations Density 0.000%

    No Known Activations