© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 221170
    Prev
    Next
    INDEX
    Explanations

    legally evidence admissibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     законода
    0.42
     맡
    0.38
     دفاتر
    0.38
     leftWheel
    0.37
    धारकों
    0.37
    ponden
    0.37
    పథ
    0.36
    事务所
    0.36
     অন্তঃ
    0.36
    🖌
    0.36
    POSITIVE LOGITS
     evidence
    0.85
     admissibility
    0.85
    Evidence
    0.80
     admissible
    0.79
     Evidence
    0.79
     inadmissible
    0.75
     EVIDENCE
    0.74
    evidence
    0.73
    证据
    0.69
     incriminating
    0.67
    Activations Density 0.013%

    No Known Activations