© 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. 199621
    Prev
    Next
    INDEX
    Explanations

    standard, aggressive

    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
     as
    0.46
    Pars
    0.45
    posing
    0.42
    rect
    0.42
    digital
    0.42
     formular
    0.41
    Rect
    0.41
    '
    0.41
    per
    0.41
    regional
    0.40
    POSITIVE LOGITS
     défis
    0.54
    目標
    0.50
     चुनौ
    0.50
     पीने
    0.50
     desafios
    0.49
     necesitar
    0.48
    ຄວ
    0.46
     respal
    0.44
    ﻪ
    0.44
     डाइट
    0.43
    Activations Density 0.004%

    No Known Activations