© 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. 1897
    Prev
    Next
    INDEX
    Explanations

    let, suppose, definition, evaluation

    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
    mény
    -0.80
    ције
    -0.80
    Tito
    -0.77
    arana
    -0.77
    وں
    -0.77
    itulo
    -0.75
     نت
    -0.74
    գ
    -0.73
    Disconnected
    -0.73
    емый
    -0.73
    POSITIVE LOGITS
     model
    1.01
     models
    0.99
    instant
    0.97
     modeling
    0.94
     function
    0.90
     Vertex
    0.90
    logistic
    0.86
     modelli
    0.83
    Modeling
    0.82
    marginal
    0.82
    Activations Density 0.047%

    No Known Activations