© 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. 80689
    Prev
    Next
    INDEX
    Explanations

    customer reviews and service

    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
    дили
    -0.84
    </table>
    -0.83
     boste
    -0.82
    ིས་
    -0.82
     finns
    -0.81
    atification
    -0.80
     actos
    -0.80
     bosons
    -0.80
     Transfermarkt
    -0.79
     bilhões
    -0.79
    POSITIVE LOGITS
     consumer
    1.27
     consumers
    1.16
    consumer
    1.11
     Consumer
    1.02
     their
    1.00
     beware
    0.93
     they
    0.92
     consumidores
    0.92
    Consumers
    0.91
    Consumer
    0.90
    Activations Density 0.010%

    No Known Activations