© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158301
    Prev
    Next
    INDEX
    Explanations

    added

    np_acts-logits-general · gemini-2.5-flash-lite

    market growth and urgency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inférieurs
    0.48
    кал
    0.46
    ेडियम
    0.45
     hulp
    0.45
    வனே
    0.43
    㦣
    0.43
     indole
    0.43
    াহিয়া
    0.43
    Flatten
    0.43
     unittest
    0.43
    POSITIVE LOGITS
    um
    0.57
    ut
    0.55
    k
    0.54
    an
    0.53
    se
    0.52
    ag
    0.52
    n
    0.51
    ur
    0.50
    y
    0.50
    ån
    0.50
    Activations Density 0.003%

    No Known Activations