© 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. 2120
    Prev
    Next
    INDEX
    Explanations

    easy handling and processing

    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
    ֵּ
    -0.88
     compositeur
    -0.86
     ayuntamiento
    -0.83
     gefertigt
    -0.81
    tacles
    -0.81
     schwarze
    -0.81
    仕組み
    -0.80
    それも
    -0.80
     décider
    -0.80
     concentr
    -0.79
    POSITIVE LOGITS
     easier
    1.44
     easy
    1.33
     easily
    1.28
     manipulation
    1.22
     ease
    1.21
     machining
    1.20
     Working
    1.18
     processing
    1.16
     manipulate
    1.16
     handling
    1.14
    Activations Density 0.091%

    No Known Activations