© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12808
    Prev
    Next
    INDEX
    Explanations

    Be

    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
    ೖ
    0.55
     بای
    0.54
    pyrrol
    0.50
    SystemFileSystem
    0.50
    綣
    0.49
     बाय
    0.47
     بان
    0.46
    伍章
    0.46
    阊
    0.46
    ጦ
    0.45
    POSITIVE LOGITS
    Be
    3.64
     BE
    3.59
    BE
    3.58
     Be
    3.50
     Bea
    3.45
     Beaver
    3.34
    be
    3.30
     beh
    3.28
     Beh
    3.28
    Bea
    3.25
    Activations Density 0.379%

    No Known Activations