© 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. 162132
    Prev
    Next
    INDEX
    Explanations

    tight guarding, tight hips

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

    fairness and inclusion

    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
    ↵
    0.59
    PA
    0.51
    Я
    0.48
    2
    0.47
    深い
    0.47
    י
    0.46
    רי
    0.46
    ้
    0.46
     PA
    0.46
    ทั้ง
    0.45
    POSITIVE LOGITS
     कॉनक
    0.50
     Scouting
    0.47
     Invoke
    0.46
     Conf
    0.46
     iskust
    0.46
     Emp
    0.45
     exploración
    0.45
     Experiences
    0.44
     probate
    0.43
     asshole
    0.43
    Activations Density 0.002%

    No Known Activations