© 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. 39868
    Prev
    Next
    INDEX
    Explanations

    twisted into

    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
     коюм
    0.47
    ”（
    0.47
    渶
    0.45
    环境保护
    0.43
     സേ
    0.43
     può
    0.42
     escuchado
    0.42
    鈳
    0.41
    늡
    0.41
     [],
    0.41
    POSITIVE LOGITS
     relaxation
    0.49
     slumber
    0.47
    mohan
    0.47
     nightmares
    0.45
     companions
    0.44
     prematurely
    0.44
            
    0.43
     Gand
    0.42
     humiliation
    0.42
     pedigree
    0.42
    Activations Density 0.013%

    No Known Activations