© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63667
    Prev
    Next
    INDEX
    Explanations

    <code>public struct</code>

    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
     //
    -2.75
    ();//
    -2.67
    ";//
    -2.64
    ");//
    -2.61
    );//
    -2.52
    ());//
    -2.44
    ];//
    -2.42
    ;//
    -2.33
    ){//
    -2.30
     {//
    -2.27
    POSITIVE LOGITS
     gynnwys
    0.90
    anders
    0.90
    nate
    0.87
     отличается
    0.85
     same
    0.84
    vereign
    0.84
    ander
    0.82
    というと
    0.82
    ligent
    0.81
    joit
    0.81
    Activations Density 0.063%

    No Known Activations