© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24454
    Prev
    Next
    INDEX
    Explanations

    higher composition laws

    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_40_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
     nantinya
    0.43
    Bobby
    0.43
    kfollowers
    0.39
     Bobby
    0.39
    lasts
    0.38
    bol
    0.38
    蛻
    0.38
     بث
    0.38
    INIS
    0.38
    窪
    0.37
    POSITIVE LOGITS
    launcher
    0.43
     Bele
    0.39
     люд
    0.38
     Pact
    0.38
    電車
    0.37
    peau
    0.37
     fell
    0.36
    amen
    0.36
    你自己
    0.36
     blew
    0.36
    Activations Density 0.000%

    No Known Activations