© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 221823
    Prev
    Next
    INDEX
    Explanations

    specific actions and technical terms

    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
     proteolytic
    0.39
    Selective
    0.38
    ванням
    0.38
    鑾
    0.38
    ];
    0.38
     multimeter
    0.37
    ণ্ডে
    0.37
    يدي
    0.37
     potency
    0.37
     outwardly
    0.37
    POSITIVE LOGITS
     bribe
    0.39
    🥳
    0.39
     даже
    0.39
     brib
    0.38
     เงิน
    0.38
    CHINA
    0.38
     ঘুষ
    0.38
    ˃
    0.38
     حتی
    0.38
    specifically
    0.38
    Activations Density 0.002%

    No Known Activations