© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228855
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ਸਾ
    0.45
    มัน
    0.42
    france
    0.42
    donation
    0.42
     Infer
    0.42
     Access
    0.41
    坨
    0.41
    server
    0.40
    the
    0.40
     Spit
    0.40
    POSITIVE LOGITS
     sincerity
    0.47
    вых
    0.47
     impover
    0.46
    を入力
    0.46
     internalization
    0.45
     imidazol
    0.45
     daños
    0.44
    ﻜ
    0.44
     olmadığını
    0.43
     evidences
    0.43
    Activations Density 0.009%

    No Known Activations