© 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. 21556
    Prev
    Next
    INDEX
    Explanations

    to do

    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
    for
    -1.59
    C
    -1.51
     how
    -1.50
    there
    -1.45
     will
    -1.40
    J
    -1.35
     or
    -1.34
     for
    -1.34
    O
    -1.31
    [
    -1.30
    POSITIVE LOGITS
    ╖
    1.52
     dezelve
    1.51
     cervello
    1.50
    댔
    1.50
    AMIENTO
    1.48
     paesaggio
    1.48
    
    1.46
    gucig
    1.43
     remarquer
    1.43
    ⢣
    1.41
    Activations Density 0.033%

    No Known Activations