© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53356
    Prev
    Next
    INDEX
    Explanations

    assist you

    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_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
     are
    0.47
     nec
    0.47
     hypoxia
    0.46
     prism
    0.45
     शी
    0.44
    參
    0.43
    itec
    0.43
     transl
    0.42
     شوند
    0.42
     edi
    0.42
    POSITIVE LOGITS
    학교
    0.49
    теря
    0.49
    Authorize
    0.49
     Paglin
    0.49
     столе
    0.47
     выборах
    0.46
     QnrB
    0.45
     Pilih
    0.45
    ('-
    0.45
    উদাহরণ
    0.45
    Activations Density 0.002%

    No Known Activations