© 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. 99730
    Prev
    Next
    INDEX
    Explanations

    specific phrases

    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
    ieważ
    -0.77
    İstinadlar
    -0.75
     debate
    -0.71
     Carlin
    -0.71
    र्य
    -0.70
     ordering
    -0.67
     outsiders
    -0.66
     randonnée
    -0.66
     corrobor
    -0.65
    モロ
    -0.65
    POSITIVE LOGITS
     MSU
    0.85
    Gradient
    0.83
     fon
    0.80
    hånd
    0.80
    скан
    0.78
    FontStyle
    0.78
    武汉
    0.78
    셰
    0.78
    Michigan
    0.77
     sigmoid
    0.77
    Activations Density 0.004%

    No Known Activations