© 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-IT
    5. 41-GEMMASCOPE-2-RES-65K
    7. 1668
    Prev
    Next
    INDEX
    Explanations

    Spanish words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    艺术
    0.73
    鐧
    0.70
    藝術
    0.70
    赵
    0.70
    嫵
    0.69
    畱
    0.68
    geoning
    0.67
     ਸਿੰ
    0.67
    驄
    0.67
     passionately
    0.65
    POSITIVE LOGITS
     usando
    1.03
     como
    0.99
     que
    0.96
     dentro
    0.95
     luego
    0.95
     puede
    0.95
     se
    0.95
     puedes
    0.91
     en
    0.90
     donde
    0.90
    Activations Density 0.700%

    No Known Activations