© 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. 217327
    Prev
    Next
    INDEX
    Explanations

    "re-", "killing", "3rd", "not differ", "in ", "and complete", "is part", ", you", "to be", "season."

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

    demonstrating your experience

    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
    唁
    0.44
    ัง
    0.42
    рті
    0.42
     transduction
    0.39
    囷
    0.39
     Stras
    0.39
     auricular
    0.39
    铑
    0.39
     intox
    0.38
    耶
    0.38
    POSITIVE LOGITS
    v
    0.50
    resources
    0.45
    af
    0.45
     çalışma
    0.44
    exemple
    0.44
    maxLength
    0.44
     trabalhar
    0.43
    exit
    0.43
    incorrect
    0.43
     সার্ভিস
    0.43
    Activations Density 0.001%

    No Known Activations