© 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-65K
    7. 50315
    Prev
    Next
    INDEX
    Explanations

    connecting ideas and clauses

    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
     ಯಾವಾಗ
    0.56
    ᒍ
    0.52
    Мы
    0.52
    我們要
    0.50
     ಪೂರ್ವ
    0.49
     हमने
    0.48
    間の
    0.48
     আমরা
    0.47
     ನಾವು
    0.47
    我們
    0.47
    POSITIVE LOGITS
    ;
    0.47
     kerana
    0.43
     karena
    0.41
     perquè
    0.40
     بسبب
    0.40
     incluyendo
    0.39
     tetapi
    0.38
     dian
    0.38
    f
    0.38
     respectivas
    0.38
    Activations Density 0.004%

    No Known Activations