© 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. 136286
    Prev
    Next
    INDEX
    Explanations

    return of product

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

    religious discrimination

    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
    ر
    0.54
    ↵↵
    0.46
    rith
    0.46
     lit
    0.45
    開始
    0.45
    er
    0.43
     ca
    0.42
    ق
    0.42
     動
    0.42
    zad
    0.41
    POSITIVE LOGITS
     hygienic
    0.48
    )="
    0.47
    Increase
    0.46
    COOL
    0.44
     медицин
    0.43
    Abbreviations
    0.43
    Chloro
    0.43
     bisc
    0.42
    Meat
    0.42
     antisymmetric
    0.42
    Activations Density 0.000%

    No Known Activations