© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59050
    Prev
    Next
    INDEX
    Explanations

    Rails associations and scopes

    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
    học
    -0.91
    🡪
    -0.89
     Оно
    -0.81
    ewon
    -0.78
    layan
    -0.77
    inių
    -0.75
    tionalität
    -0.74
     parvenir
    -0.72
    .---
    -0.71
     cyclisme
    -0.71
    POSITIVE LOGITS
     before
    1.11
     scopes
    1.05
     scope
    1.02
     callbacks
    0.99
    scope
    0.98
    scopes
    0.97
     concerned
    0.92
     relation
    0.90
     has
    0.90
    Bel
    0.88
    Activations Density 0.086%

    No Known Activations