© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46383
    Prev
    Next
    INDEX
    Explanations

    correcting errors and corruption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    ور
    0.86
    ول
    0.68
    ক
    0.64
    ){
    0.64
     assassin
    0.64
    การ
    0.62
    是一個
    0.59
    ك
    0.59
     intermediaries
    0.59
     constants
    0.57
    POSITIVE LOGITS
    Cor
    0.93
    Corr
    0.81
    cor
    0.76
    corollary
    0.75
     COR
    0.72
     Kor
    0.72
     corre
    0.71
    corr
    0.71
    Кор
    0.71
     Cor
    0.71
    Activations Density 0.036%

    No Known Activations