© 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. 17521
    Prev
    Next
    INDEX
    Explanations

    actions against opponents

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

    disrupting 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
     رجسٹر
    0.42
     عب
    0.42
    acée
    0.41
     ऑर्
    0.38
     reservados
    0.38
     કર્યું
    0.38
    慈善
    0.38
    ྨ
    0.38
     பணியாற்ற
    0.38
     Became
    0.37
    POSITIVE LOGITS
     enemy
    0.90
     opponent
    0.87
    敵人
    0.85
     enemies
    0.82
     foes
    0.81
     दुश्मन
    0.80
     opponents
    0.79
    敵
    0.79
     foe
    0.77
    敌人
    0.77
    Activations Density 0.135%

    No Known Activations