© 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. 67136
    Prev
    Next
    INDEX
    Explanations

    serial device configuration

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

    emotions or concepts

    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
    設け
    0.48
    など
    0.46
    த்து
    0.45
    𓍊
    0.43
     gratuit
    0.43
    なども
    0.43
    ೮
    0.42
    दि
    0.42
    ან
    0.42
    ᑯ
    0.42
    POSITIVE LOGITS
    érience
    0.43
    Voltage
    0.43
     Eigenschaften
    0.42
    Username
    0.42
     deinem
    0.42
     সরকারকে
    0.41
     السبب
    0.41
     Voltage
    0.41
     അടിസ്ഥാന
    0.41
     عليك
    0.40
    Activations Density 0.002%

    No Known Activations