© 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. 32027
    Prev
    Next
    INDEX
    Explanations

    move or question

    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
    Rent
    -0.78
     rental
    -0.75
     rentals
    -0.73
     rented
    -0.71
     Seward
    -0.71
    RENT
    -0.70
    covers
    -0.69
    ཏ
    -0.67
     rent
    -0.66
    業者
    -0.65
    POSITIVE LOGITS
     appart
    0.94
     pianist
    0.89
    agian
    0.86
    ayuno
    0.82
     wardrobe
    0.81
    showAlert
    0.80
    cô
    0.79
     Shade
    0.78
    faat
    0.77
    ganti
    0.77
    Activations Density 0.006%

    No Known Activations