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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30662
    Prev
    Next
    INDEX
    Explanations

    SCP containment anomalous objects

    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
    ා
    -0.77
    Buffy
    -0.77
    nacional
    -0.75
    Yoda
    -0.74
     quotient
    -0.73
     Helmet
    -0.73
     chọn
    -0.71
     gover
    -0.71
    カッコ
    -0.70
    投影
    -0.70
    POSITIVE LOGITS
     SCP
    1.69
     containment
    1.68
    SCP
    1.58
    scp
    1.27
     Containment
    1.24
     Foundation
    1.21
     anomalous
    1.20
     scp
    1.19
     contain
    1.05
     fundación
    1.05
    Activations Density 0.006%

    No Known Activations