© 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. 174436
    Prev
    Next
    INDEX
    Explanations

    macaron or macaroon

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

    attempt to describe or analyze

    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
    ن
    0.62
    מ
    0.61
    <0xAB>
    0.55
    ش
    0.53
    mod
    0.52
    ми
    0.50
    牙
    0.48
    Ref
    0.47
    不
    0.47
    ре
    0.46
    POSITIVE LOGITS
     माध्य
    0.51
     chum
    0.51
     Marie
    0.50
     FAO
    0.50
     Madam
    0.49
     rique
    0.49
     Mahogany
    0.49
     jí
    0.48
     Walmart
    0.48
     Bá
    0.47
    Activations Density 0.001%

    No Known Activations