© 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. 58634
    Prev
    Next
    INDEX
    Explanations

    popular searches and surnames

    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
    =========
    -0.87
    kein
    -0.85
     venir
    -0.84
     Properly
    -0.77
     birds
    -0.76
    лени
    -0.74
    ruler
    -0.73
    IMENT
    -0.71
    oughton
    -0.71
    ==========
    -0.71
    POSITIVE LOGITS
     mell
    0.82
    eningrad
    0.77
    ieza
    0.73
     Röntgen
    0.71
    ätte
    0.70
    溶
    0.70
     ψ
    0.69
    were
    0.68
     经
    0.68
     Rew
    0.67
    Activations Density 0.028%

    No Known Activations