© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67386
    Prev
    Next
    INDEX
    Explanations

    chmod, file permissions, protecting

    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_10/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
     was
    -1.41
     whom
    -1.36
     inox
    -1.34
    >
    -1.27
     roue
    -1.25
     Then
    -1.23
     taxe
    -1.22
                           
    -1.22
     lequel
    -1.21
     ‘
    -1.18
    POSITIVE LOGITS
    ↵
    1.41
     Apakah
    1.41
    Mitar
    1.40
     Setelah
    1.40
     Bagaimana
    1.40
     cerdas
    1.39
     modificare
    1.37
    Andere
    1.36
     menceritakan
    1.36
    Probably
    1.35
    Activations Density 0.018%

    No Known Activations