© 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. 209112
    Prev
    Next
    INDEX
    Explanations

    Espí, Celltype, Islas

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining methods or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     cycle
    0.48
    nt
    0.48
     public
    0.45
     res
    0.45
     generation
    0.45
     transformative
    0.45
    }
    0.45
     hj
    0.45
     definition
    0.44
     rejection
    0.44
    POSITIVE LOGITS
     Espí
    0.52
    ப்ச
    0.51
     lanceol
    0.51
    getCell
    0.50
     Obispo
    0.50
    ਾਬ
    0.50
    Celltype
    0.49
    esterno
    0.49
     அம்ச
    0.48
     Islas
    0.48
    Activations Density 0.001%

    No Known Activations