© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1702
    Prev
    Next
    INDEX
    Explanations

    answer or value selections

    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_16k_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
    ВА
    0.50
    gelijk
    0.48
     ट्रॉपिकल
    0.47
    વ
    0.46
    ﻠ
    0.46
    <unused2049>
    0.46
    MyToolkit
    0.46
    Escol
    0.45
    Databaze
    0.45
    <unused917>
    0.45
    POSITIVE LOGITS
     data
    0.49
     WhatsApp
    0.47
     x
    0.45
     a
    0.43
     Thursday
    0.43
     KPIs
    0.43
    _
    0.43
     $
    0.42
     X
    0.41
     customer
    0.40
    Activations Density 0.703%

    No Known Activations