© 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. 8796
    Prev
    Next
    INDEX
    Explanations

    Share your

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

    perpetuate stereotypes

    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
    prim
    0.50
    ви
    0.48
    ffic
    0.47
    কর্ম
    0.47
    plug
    0.46
     patchwork
    0.45
    вини
    0.45
    -
    0.44
     makeover
    0.44
    ksom
    0.44
    POSITIVE LOGITS
     प्रमाणात
    0.63
    .*/
    0.52
     eigenfunctions
    0.51
    ূট
    0.50
     thisobject
    0.50
    篑
    0.50
    㧔
    0.48
     কাত
    0.48
     geschaffen
    0.48
     เมตร
    0.47
    Activations Density 0.000%

    No Known Activations