© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112810
    Prev
    Next
    INDEX
    Explanations

    deceptive practices, sophisticated chatbots, wearable patches

    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_31_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
    0
    0.53
    ins
    0.52
     పై
    0.49
     lineups
    0.48
    无效
    0.47
    Error
    0.45
    readers
    0.45
    ass
    0.43
            
    0.43
    d
    0.43
    POSITIVE LOGITS
     Carls
    0.52
    남
    0.49
     Güney
    0.48
     Rwanda
    0.48
     organismo
    0.48
     Öl
    0.47
    
    0.47
     Lithuania
    0.46
     Atlético
    0.46
     Istituto
    0.45
    Activations Density 0.002%

    No Known Activations