© 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. 13977
    Prev
    Next
    INDEX
    Explanations

    ap

    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
    ன்த
    0.51
    璉
    0.50
    UserRootDir
    0.49
    抠
    0.49
    Ⲡ
    0.48
    દાવાદ
    0.47
    焱
    0.46
    ˵
    0.46
    utacji
    0.45
    ভিশ
    0.44
    POSITIVE LOGITS
     ap
    3.92
     AP
    3.84
     Ap
    3.81
    Ap
    3.63
     ап
    3.63
    AP
    3.59
    ap
    3.42
     апо
    3.38
     APO
    3.34
     آپ
    3.31
    Activations Density 0.459%

    No Known Activations