© 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. 253759
    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
    atenin
    0.53
    如果我们
    0.52
     сі
    0.49
    aminar
    0.46
    =(-
    0.45
     центра
    0.45
     刺繍
    0.45
    ِب
    0.44
    =("
    0.43
    کنندگان
    0.42
    POSITIVE LOGITS
    ى
    0.52
     Nesta
    0.51
     Wohn
    0.51
     mês
    0.51
    栻
    0.48
     Rafał
    0.48
     Rafa
    0.47
     Pierws
    0.47
    𝗷
    0.46
    接下來
    0.46
    Activations Density 0.000%

    No Known Activations