© 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. 126381
    Prev
    Next
    INDEX
    Explanations

    functional explanation, projects

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    VIN
    0.41
     zumindest
    0.39
     Ret
    0.39
     AED
    0.39
     siquiera
    0.39
    NLP
    0.39
     *
    0.39
    Vincent
    0.39
    屿
    0.38
    总结
    0.38
    POSITIVE LOGITS
     Pemer
    0.52
    حضرت
    0.49
    পারে
    0.48
    icots
    0.48
     ਇ
    0.46
    Therates
    0.45
     ਰ
    0.44
     ハンド
    0.44
     pemerintahan
    0.44
    iler
    0.44
    Activations Density 0.000%

    No Known Activations