© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1028
    Prev
    Next
    INDEX
    Explanations

    has/have set

    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
     ExecuteAsync
    -0.80
    ี้ยง
    -0.77
    Созда
    -0.73
    梱
    -0.72
    viere
    -0.72
    illante
    -0.71
     cráneo
    -0.69
    强调
    -0.68
    yla
    -0.68
    ικές
    -0.68
    POSITIVE LOGITS
     sights
    3.66
     eyes
    2.95
    sights
    2.27
    eyes
    2.23
     eye
    2.03
     sight
    1.99
     eyeing
    1.98
    目光
    1.94
    Eyes
    1.81
     Eyes
    1.73
    Activations Density 0.022%

    No Known Activations