© 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. 258813
    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
     լ
    0.44
     boj
    0.42
     bolstering
    0.42
     monolayer
    0.39
    졸
    0.39
    ্যু
    0.38
     marred
    0.38
     polož
    0.37
    崩溃
    0.37
    izumab
    0.37
    POSITIVE LOGITS
    at
    0.62
    ين
    0.51
     Еўропы
    0.49
     Glück
    0.48
    Sco
    0.48
    त
    0.48
     आवि
    0.47
    ert
    0.45
    Community
    0.45
     पंड
    0.45
    Activations Density 1.681%

    No Known Activations