© 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. 111026
    Prev
    Next
    INDEX
    Explanations

    related to user interactions

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

    initiator or system component

    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
    備
    0.44
    threads
    0.43
    略
    0.42
    fields
    0.42
    dlg
    0.42
    தம்
    0.41
    agre
    0.41
    fing
    0.41
     dukkham
    0.41
    與
    0.41
    POSITIVE LOGITS
    duğu
    0.61
    ພວກເຮ
    0.54
    ایط
    0.50
    ﻙ
    0.48
     पार्किंग
    0.47
     ipotesi
    0.47
     বয়সী
    0.46
     পুড়ে
    0.46
     भूले
    0.46
     egli
    0.46
    Activations Density 0.002%

    No Known Activations