© 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. 108509
    Prev
    Next
    INDEX
    Explanations

    creators and developers

    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
     ciepła
    -0.88
    Patients
    -0.84
    *********/
    -0.82
     Patients
    -0.80
    ついた
    -0.79
    |
    -0.77
    icône
    -0.77
    Ⅽ
    -0.77
     réfugiés
    -0.75
    ėti
    -0.75
    POSITIVE LOGITS
     designers
    4.69
     developers
    4.69
     creators
    4.34
     makers
    3.64
     producers
    3.59
     developer
    3.17
     filmmakers
    3.02
     creator
    2.92
     authors
    2.91
    developers
    2.89
    Activations Density 0.200%

    No Known Activations