© 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. 64518
    Prev
    Next
    INDEX
    Explanations

    either version

    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
     indispensables
    -0.78
     sickness
    -0.75
     viss
    -0.74
    珀
    -0.69
     malade
    -0.69
     remarquable
    -0.69
     fij
    -0.68
     repo
    -0.68
    DAILY
    -0.68
    kosti
    -0.68
    POSITIVE LOGITS
     appropriately
    0.80
     originally
    0.75
     Acacia
    0.74
     finalizar
    0.73
     provider
    0.70
     розташо
    0.70
     была
    0.70
    וצ
    0.69
    чі
    0.69
    udur
    0.69
    Activations Density 0.038%

    No Known Activations