© 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. 1354
    Prev
    Next
    INDEX
    Explanations

    design patterns

    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
     Selecciona
    -0.96
     issu
    -0.78
     Lleva
    -0.72
    دد
    -0.71
     More
    -0.71
    MC
    -0.69
    Accessible
    -0.69
    잇
    -0.68
     Pueden
    -0.67
     Incluye
    -0.66
    POSITIVE LOGITS
    Memento
    0.84
    lottes
    0.84
    rajz
    0.82
    ᚷ
    0.81
     component
    0.79
     imidlertid
    0.79
    ˅
    0.79
    amem
    0.78
    ều
    0.76
     composite
    0.76
    Activations Density 0.012%

    No Known Activations