© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8152
    Prev
    Next
    INDEX
    Explanations

    uppercase and lowercase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
    纳米
    0.56
    ፊት
    0.55
     enseign
    0.52
    撐
    0.52
     nanoparticles
    0.51
    వల
    0.50
     바라
    0.50
     সচিব
    0.50
    彠
    0.49
     מיט
    0.49
    POSITIVE LOGITS
     uppercase
    2.17
     lowercase
    2.16
     capital
    2.11
     capitalized
    1.98
    Capital
    1.95
     capitals
    1.95
    capital
    1.93
    uppercase
    1.93
     Capital
    1.91
    UpperCase
    1.87
    Activations Density 0.360%

    No Known Activations