© 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-65K
    7. 51096
    Prev
    Next
    INDEX
    Explanations

    financial formulas and multilingual terms

    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
    嫣
    0.47
    Pain
    0.46
    oclaw
    0.41
    до
    0.41
     ജീവിത
    0.40
    ों
    0.40
     nyeri
    0.40
     Pain
    0.40
    ાર
    0.39
    碐
    0.39
    POSITIVE LOGITS
     antaranya
    0.42
     editing
    0.41
    editing
    0.41
     Deux
    0.41
     leveraging
    0.39
     française
    0.39
    으로는
    0.38
    Deux
    0.38
     ப்ர
    0.37
    edu
    0.37
    Activations Density 0.003%

    No Known Activations