© 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. 76628
    Prev
    Next
    INDEX
    Explanations

    python unicode_literals import

    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
     cellars
    -0.81
    pady
    -0.72
     bungalows
    -0.72
     rechange
    -0.69
    iStock
    -0.69
     wrecking
    -0.68
    idalgo
    -0.68
    Ȝ
    -0.67
    Enroll
    -0.67
     righe
    -0.67
    POSITIVE LOGITS
     freshwater
    0.69
     Shy
    0.68
    LCD
    0.67
    LSB
    0.66
    yı
    0.66
     Forster
    0.65
     Differenz
    0.65
    mering
    0.65
     Pac
    0.64
    fresh
    0.64
    Activations Density 0.110%

    No Known Activations