© 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. 14145
    Prev
    Next
    INDEX
    Explanations

    task or process

    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
    iter
    0.61
    rist
    0.57
    lessly
    0.56
    像
    0.56
    rican
    0.56
    墮
    0.53
    iai
    0.52
    っていて
    0.52
    äre
    0.52
    щаются
    0.51
    POSITIVE LOGITS
    <0xDD>
    0.59
     remedied
    0.54
    課題
    0.53
     dissection
    0.51
     utilized
    0.50
     utilization
    0.50
     Slash
    0.50
     SLASH
    0.50
     FOUND
    0.50
    ̫
    0.49
    Activations Density 0.000%

    No Known Activations