© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5619
    Prev
    Next
    INDEX
    Explanations

    Pearl Harbor, flagged, rebound, fetish, contract, Earth, USD, rickshaw, manifesting

    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_16k_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
    b
    0.55
      
    0.54
    s
    0.54
     '
    0.52
    v
    0.52
     F
    0.51
    t
    0.51
     C
    0.50
     high
    0.47
     is
    0.47
    POSITIVE LOGITS
     môžete
    0.55
     želite
    0.52
     уйнагыз
    0.50
     wikipagina
    0.50
    abbanti
    0.49
     umíst
    0.48
    ক্ষিতে
    0.48
     možete
    0.47
     koristiti
    0.47
     уйнау
    0.47
    Activations Density 0.012%

    No Known Activations