© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112810
    Prev
    Next
    INDEX
    Explanations

    Spanish welcome

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

    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-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
    0
    0.56
    ins
    0.49
     పై
    0.47
    无效
    0.46
     lineups
    0.45
    Statements
    0.45
    readers
    0.45
            
    0.44
    lin
    0.44
                 
    0.44
    POSITIVE LOGITS
     Güney
    0.55
    남
    0.52
     Atlético
    0.50
     Carls
    0.50
    
    0.49
     Slovakia
    0.49
     Conseils
    0.49
     organismo
    0.48
     Rwanda
    0.48
     Istituto
    0.48
    Activations Density 0.000%

    No Known Activations