© 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. 79104
    Prev
    Next
    INDEX
    Explanations

    cut, copy, paste

    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
    🚵
    -0.73
    wink
    -0.72
    ीडियो
    -0.71
    ulink
    -0.71
     дъ
    -0.71
     polynomial
    -0.70
    洗い
    -0.69
     bagged
    -0.69
    lée
    -0.69
     AsyncTask
    -0.69
    POSITIVE LOGITS
     paste
    3.09
     Paste
    2.81
    paste
    2.69
    Paste
    2.56
     pasting
    2.47
     pasted
    2.39
     cut
    1.79
     collage
    1.60
     Cut
    1.53
    cut
    1.47
    Activations Density 0.030%

    No Known Activations