© 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
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13888
    Prev
    Next
    INDEX
    Explanations

    A

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    !
    0.72
     similar
    0.70
     considerably
    0.65
    :
    0.62
     identical
    0.60
     icing
    0.57
     significantly
    0.57
     such
    0.56
    类似的
    0.56
    <sup>
    0.56
    POSITIVE LOGITS
     Tale
    1.08
     tale
    1.06
     Memoir
    1.03
     GUIDE
    1.03
     Journey
    0.97
     Treatise
    0.97
     História
    0.96
     Tribute
    0.93
     Introduction
    0.91
     törté
    0.91
    Activations Density 0.063%

    No Known Activations