© 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. 77652
    Prev
    Next
    INDEX
    Explanations

    defense and legal proceedings

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

    defend, argue, blame

    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
     ለአ
    0.42
     approving
    0.40
    য়োজন
    0.39
    ွမ်း
    0.37
    嫉
    0.37
     fermentum
    0.37
     thúc
    0.36
    授予
    0.36
    鉴
    0.36
     চক্ষু
    0.35
    POSITIVE LOGITS
     defended
    0.99
     defend
    0.96
     defending
    0.96
     defends
    0.91
    防御
    0.91
     savun
    0.86
     defense
    0.86
     defensive
    0.85
     defenses
    0.85
     دفاع
    0.85
    Activations Density 0.221%

    No Known Activations