© 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. 158338
    Prev
    Next
    INDEX
    Explanations

    findings, symptoms, or results

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

    racist, corrections, sport, resting

    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
    ERI
    0.51
    ,
    0.50
     reliably
    0.41
     efficiently
    0.40
    具合
    0.40
     energ
    0.39
    ),
    0.39
    ఱ
    0.38
     autonomously
    0.38
     using
    0.38
    POSITIVE LOGITS
    avacanam
    0.47
     नकारात्मक
    0.46
     улучшения
    0.46
     आईपीएस
    0.43
     mejoras
    0.43
     निकाला
    0.42
     প্রত্যাখ্যান
    0.42
     хорошие
    0.42
     ไอ้
    0.41
    Pant
    0.41
    Activations Density 0.002%

    No Known Activations