© 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. 128607
    Prev
    Next
    INDEX
    Explanations

    vertical alignment

    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
    
    -1.56
    戗
    -1.46
    筇
    -1.45
    鸸
    -1.45
    WithMany
    -1.44
     borbo
    -1.43
     beſt
    -1.41
     molte
    -1.41
    pti
    -1.41
    atime
    -1.40
    POSITIVE LOGITS
     eight
    1.48
    D
    1.46
     stellar
    1.45
     resolute
    1.42
    As
    1.42
     unrelenting
    1.41
                
    1.40
     so
    1.38
    am
    1.37
     rudimentary
    1.36
    Activations Density 0.005%

    No Known Activations