© 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. 73412
    Prev
    Next
    INDEX
    Explanations

    closing bracket followed by brace or comment

    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
    quels
    -1.31
     certaines
    -1.30
     både
    -1.26
     کامل
    -1.25
     indien
    -1.23
     quoque
    -1.21
    arns
    -1.20
    THOR
    -1.20
    ASKA
    -1.19
     ‘’
    -1.16
    POSITIVE LOGITS
     that
    2.06
     this
    1.48
     relatively
    1.45
     allows
    1.43
     analysis
    1.41
     important
    1.41
     data
    1.38
     Actually
    1.35
     enormously
    1.34
     actually
    1.34
    Activations Density 0.041%

    No Known Activations