© 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. 13604
    Prev
    Next
    INDEX
    Explanations

    right

    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
    右
    1.47
     RIGHT
    1.37
    左
    1.37
     left
    1.34
     pravo
    1.33
     오른쪽
    1.32
     righth
    1.31
     右
    1.30
     Right
    1.30
     derecho
    1.30
    POSITIVE LOGITS
    对
    1.24
    對
    1.24
     对
    1.05
     對
    0.84
     đối
    0.81
    对其
    0.80
     rig
    0.79
    対
    0.79
    ถูก
    0.72
    是对
    0.71
    Activations Density 0.041%

    No Known Activations