© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45649
    Prev
    Next
    INDEX
    Explanations

    internet security sandbox

    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
     juris
    -0.81
     vecchia
    -0.79
     kertas
    -0.79
     הני
    -0.78
     зру
    -0.74
    發
    -0.73
     RSSSF
    -0.73
     lignes
    -0.71
    owohl
    -0.71
    Roasted
    -0.71
    POSITIVE LOGITS
     security
    1.64
     trusted
    1.60
     güven
    1.35
     policy
    1.32
     sandbox
    1.30
     Trusted
    1.28
     Trust
    1.27
    trusted
    1.27
     trust
    1.25
     Security
    1.25
    Activations Density 0.118%

    No Known Activations