© 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. 59536
    Prev
    Next
    INDEX
    Explanations

    price and sale price

    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
    نه
    -0.88
    asta
    -0.84
     Conselho
    -0.81
    客
    -0.80
     them
    -0.79
     zamknię
    -0.77
     نه
    -0.75
     It
    -0.75
     Developed
    -0.75
    apture
    -0.74
    POSITIVE LOGITS
    &$
    0.93
    recently
    0.85
    jabat
    0.84
    стры
    0.82
    |$
    0.82
     $/
    0.81
    ——————
    0.81
    <0xE3>
    0.81
     savings
    0.80
    леко
    0.80
    Activations Density 0.016%

    No Known Activations