© 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. 39742
    Prev
    Next
    INDEX
    Explanations

    official procedures and analysis

    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
    ting
    0.50
     달
    0.49
     the
    0.49
     to
    0.48
     taste
    0.47
    ed
    0.47
     smelled
    0.46
     smell
    0.46
    색
    0.45
     S
    0.45
    POSITIVE LOGITS
    جراء
    0.55
     parcial
    0.52
     oficiales
    0.52
     gerenci
    0.52
     offizi
    0.50
     Verfahren
    0.49
     führen
    0.48
     partielle
    0.48
     racionais
    0.47
    领先
    0.47
    Activations Density 0.016%

    No Known Activations