© 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. 13622
    Prev
    Next
    INDEX
    Explanations

    enter, blank space

    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
    براین
    0.56
    FORD
    0.54
    पेश
    0.54
    ങ്കി
    0.54
     $(
    0.53
    )\\
    0.53
    ')){
    0.52
     कैंप
    0.51
    )^{*}
    0.51
    వరి
    0.51
    POSITIVE LOGITS
     Enter
    1.18
     enter
    1.16
    Enter
    1.10
    enter
    1.08
    _______
    1.00
    ENTER
    0.98
     _______
    0.97
    ____________
    0.96
    ______
    0.96
     entered
    0.95
    Activations Density 0.004%

    No Known Activations