© 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. 15621
    Prev
    Next
    INDEX
    Explanations

    empirical experience

    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
    ल्पना
    0.58
    ]";
    0.57
    WindowConstants
    0.54
     соотно
    0.53
    etra
    0.50
     زینت
    0.50
    ')";
    0.50
    quart
    0.49
    プチ
    0.49
     हाउ
    0.48
    POSITIVE LOGITS
    VIR
    0.66
    Emp
    0.63
     Emp
    0.62
     अनुभव
    0.59
    EMP
    0.59
     empowered
    0.57
    鎵
    0.57
     barking
    0.57
     empir
    0.55
    paralleled
    0.55
    Activations Density 0.000%

    No Known Activations