© 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. 83574
    Prev
    Next
    INDEX
    Explanations

    compensation insurance, jurisprudence, denial

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

    explaining complex logic

    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
    ekeeping
    0.42
    ৃ
    0.42
     tucked
    0.42
    லீ
    0.41
    бо
    0.40
     ethics
    0.40
    osy
    0.40
     turned
    0.39
     Performance
    0.39
     rigid
    0.39
    POSITIVE LOGITS
    コレ
    0.52
     Compens
    0.52
    EPC
    0.51
     μεγ
    0.50
     Ա
    0.50
    EMPLOY
    0.50
    この
    0.50
     Bxf
    0.49
     Высо
    0.49
     EPC
    0.48
    Activations Density 0.000%

    No Known Activations