© 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. 69864
    Prev
    Next
    INDEX
    Explanations

    before Trump

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

    process actions and their contexts

    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
     פּ
    0.39
    су
    0.36
    е
    0.36
    ке
    0.34
    さまざまな
    0.34
     বাসিন্দ
    0.34
     असंख्य
    0.34
    ні
    0.34
     нередко
    0.34
    த்தின்
    0.33
    POSITIVE LOGITS
     اخر
    0.48
     recieved
    0.47
     ঘোষনা
    0.46
     McDonalds
    0.46
     loosing
    0.45
    劵
    0.42
    postion
    0.41
     हमे
    0.40
    রাষ্ট
    0.40
     পরবর্ত
    0.39
    Activations Density 0.036%

    No Known Activations