© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134448
    Prev
    Next
    INDEX
    Explanations

    intriguing, surprising, fascinating

    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_40_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
    ጢ
    0.40
    거든
    0.39
     കൂട്ട
    0.38
    这些人
    0.38
    ਧ
    0.38
    うち
    0.37
    blätter
    0.37
     initially
    0.37
     fopen
    0.37
    ｋ
    0.37
    POSITIVE LOGITS
     überras
    0.54
     interesantes
    0.52
     intriguing
    0.51
     surprising
    0.50
     surprises
    0.50
     Surprise
    0.48
     fascinating
    0.48
     exciting
    0.47
     thrilling
    0.47
     sorprend
    0.46
    Activations Density 0.002%

    No Known Activations