© 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. 23008
    Prev
    Next
    INDEX
    Explanations

    opposition and enemies

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

    enemies and opponents

    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
    ي
    0.73
    يت
    0.70
    ন
    0.67
    دە
    0.67
    ח
    0.66
    ن
    0.63
    hadas
    0.62
    ্ী
    0.61
    স
    0.61
    த்துள்
    0.59
    POSITIVE LOGITS
     opposition
    1.01
     دشمن
    0.96
    Opposition
    0.93
    敵
    0.91
     Opposition
    0.88
     enemies
    0.86
    opposition
    0.86
     enemy
    0.85
    Enemy
    0.83
    敌
    0.82
    Activations Density 0.031%

    No Known Activations