© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66062
    Prev
    Next
    INDEX
    Explanations

    memory protection function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    यं
    -0.81
    RICAL
    -0.78
    ieteur
    -0.77
     Kopp
    -0.77
    ₂
    -0.76
     Hr
    -0.75
    uli
    -0.74
    PX
    -0.73
     Twit
    -0.73
    iya
    -0.71
    POSITIVE LOGITS
     techniques
    1.00
     hardware
    0.78
     tabled
    0.77
    佑
    0.74
     detection
    0.74
     schemes
    0.73
    CurrentValue
    0.73
     DETECTION
    0.73
     scheme
    0.73
     TECHNIQUES
    0.73
    Activations Density 0.038%

    No Known Activations