© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26525
    Prev
    Next
    INDEX
    Explanations

    location or effect

    np_acts-logits-general · gemini-2.5-flash-lite

    learning resources and tutorials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ফ্লাইট
    0.52
     অব্যাহত
    0.51
     BlueprintName
    0.48
     설립
    0.47
    ﻌ
    0.47
     資
    0.46
     ਜਾ
    0.46
    НЫ
    0.46
     eigenstates
    0.45
    ওয়ার
    0.44
    POSITIVE LOGITS
     sporty
    0.47
     small
    0.47
     gambar
    0.47
     web
    0.46
     eco
    0.46
     kecil
    0.46
     FC
    0.46
     gyroscope
    0.45
     elet
    0.45
     canoe
    0.44
    Activations Density 0.000%

    No Known Activations