© 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. 66913
    Prev
    Next
    INDEX
    Explanations

    checking if something is an array

    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
    yon
    -1.44
     incluse
    -1.43
    -¡
    -1.43
    
    -1.41
     baumwolle
    -1.39
    hanced
    -1.36
     própri
    -1.35
     garcia
    -1.34
     ſur
    -1.33
     zostały
    -1.30
    POSITIVE LOGITS
    9
    1.83
     him
    1.79
     this
    1.64
    4
    1.55
    ovina
    1.53
    6
    1.46
     bunun
    1.45
     how
    1.45
     it
    1.44
    っしゃ
    1.43
    Activations Density 0.018%

    No Known Activations