© 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. 34-GEMMASCOPE-RES-131K
    7. 118429
    Prev
    Next
    INDEX
    Explanations

    constructor parameters with underscore prefix

    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_34/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
     jego
    -1.06
     его
    -1.04
     seinem
    -1.00
     він
    -0.96
     his
    -0.95
    His
    -0.95
     його
    -0.87
     suoi
    -0.85
    ●
    -0.84
     ansehen
    -0.84
    POSITIVE LOGITS
     $\
    2.55
     $_
    1.71
     _
    1.66
    :_
    1.60
    =$_
    1.51
    (_
    1.46
     Mrs
    1.41
     Ms
    1.39
     {_
    1.38
     &_
    1.34
    Activations Density 0.026%

    No Known Activations