© 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. 58551
    Prev
    Next
    INDEX
    Explanations

    Laverne, Tuesday

    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
     it
    -1.86
     pokoje
    -1.52
    ==""){
    -1.50
    mässig
    -1.48
     tevreden
    -1.48
     Königin
    -1.47
    他們
    -1.46
    cedula
    -1.45
     or
    -1.44
     jejich
    -1.44
    POSITIVE LOGITS
    ↵↵
    1.70
    estries
    1.47
    ignment
    1.46
    і
    1.41
    яв
    1.33
    ↵↵↵
    1.31
    但在
    1.30
    ppan
    1.30
    都是在
    1.29
    uo
    1.28
    Activations Density 0.016%

    No Known Activations