© 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. 206840
    Prev
    Next
    INDEX
    Explanations

    divided into, analysis of, any racism

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

    define structure or improve accuracy

    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
    evo
    0.46
    op
    0.43
    VX
    0.42
    狡
    0.42
    дор
    0.40
    层
    0.40
    ី
    0.40
    ៤
    0.40
    सर्ग
    0.40
    饪
    0.40
    POSITIVE LOGITS
     атмос
    0.52
     assolutamente
    0.49
     upside
    0.48
     cumul
    0.46
     outfit
    0.46
     تس
    0.43
     Magnificent
    0.43
     swing
    0.42
     本当
    0.42
     جار
    0.41
    Activations Density 0.001%

    No Known Activations