© 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. 201671
    Prev
    Next
    INDEX
    Explanations

    two million

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

    systemic discrimination, oppression, racism

    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
    还可以
    0.44
    arton
    0.43
    可能な
    0.42
    Joshua
    0.42
    చ్
    0.42
    нын
    0.42
    生产
    0.42
    Ꮓ
    0.42
    મના
    0.41
    শ্ত
    0.41
    POSITIVE LOGITS
    ضة
    0.47
     وكانت
    0.46
     gave
    0.46
     تردد
    0.46
     was
    0.45
     అక్కడ
    0.43
     came
    0.42
     baku
    0.42
     reportedly
    0.41
     안에
    0.41
    Activations Density 0.002%

    No Known Activations