© 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. 12584
    Prev
    Next
    INDEX
    Explanations

    import qualified use alias

    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
    አ
    0.50
    T
    0.47
    A
    0.47
    ്യൂ
    0.46
    STRA
    0.45
     format
    0.43
     approfond
    0.43
    IOS
    0.41
     （
    0.41
    fy
    0.40
    POSITIVE LOGITS
     τησ
    0.48
     exacta
    0.47
    ުން
    0.43
    ouer
    0.43
     выполнить
    0.43
    elv
    0.43
    ոն
    0.42
    меня
    0.41
    чә
    0.41
    ো
    0.41
    Activations Density 0.001%

    No Known Activations