© 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. 7242
    Prev
    Next
    INDEX
    Explanations

    legal defendants and court proceedings

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

    legal cases and proceedings

    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
     سیستم
    0.47
     Tarifleri
    0.46
     বিশ্বের
    0.46
    运营
    0.41
    क्यूमेंट
    0.40
     copyspace
    0.40
     Europas
    0.39
    😍
    0.39
     نمایش
    0.39
     તૈય
    0.39
    POSITIVE LOGITS
     appellant
    0.70
     pretrial
    0.69
     appellate
    0.67
     evidentiary
    0.67
     defendant
    0.66
     defendants
    0.65
     Appellant
    0.64
     codef
    0.64
     Defendant
    0.63
     appellants
    0.63
    Activations Density 0.153%

    No Known Activations