© 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-262K
    7. 200819
    Prev
    Next
    INDEX
    Explanations

    personal interests and enjoyment

    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_262k_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
    キスト
    0.44
     unsett
    0.44
    𝖚
    0.42
    கர்
    0.42
     pełni
    0.42
    ាតុ
    0.41
    ದ್ಧ
    0.41
     portrays
    0.41
     isAuthenticated
    0.41
     extracellular
    0.40
    POSITIVE LOGITS
     began
    0.45
     право
    0.42
     ①
    0.40
     tava
    0.40
     hauling
    0.40
     عمران
    0.38
    㓡
    0.38
     FIN
    0.38
     Brazilian
    0.37
     уско
    0.37
    Activations Density 0.006%

    No Known Activations