© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 144408
    Prev
    Next
    INDEX
    Explanations

    code and technical explanations

    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
    ید
    0.54
    لی
    0.50
    یا
    0.49
     Premises
    0.48
    College
    0.47
    Attractive
    0.46
    </h4>
    0.44
    Casual
    0.43
    ﻭ
    0.42
    ند
    0.42
    POSITIVE LOGITS
     gelatin
    0.49
    cretion
    0.47
     hauling
    0.46
     thorax
    0.46
    ucose
    0.44
    ক্ষিতে
    0.44
     slowly
    0.43
     slowed
    0.43
     MFG
    0.43
     stretchy
    0.43
    Activations Density 0.003%

    No Known Activations