© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17196
    Prev
    Next
    INDEX
    Explanations

    protection and shielding

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

    protection and its contexts

    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_53_width_65k_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
    ;%(
    0.42
    プロセス
    0.41
     impresionante
    0.41
    ंड
    0.39
    ceğini
    0.39
    ヂストン
    0.39
     impressive
    0.39
    얹
    0.39
    清新
    0.39
     introducir
    0.39
    POSITIVE LOGITS
     shield
    0.89
     afforded
    0.79
     shields
    0.78
     against
    0.77
     shielding
    0.74
     Shield
    0.69
    伞
    0.68
    Against
    0.68
    against
    0.67
    shield
    0.66
    Activations Density 0.033%

    No Known Activations