© 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. 38533
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
    echt
    -0.82
     jarak
    -0.79
     Klasse
    -0.76
    encana
    -0.73
     группу
    -0.72
    endorf
    -0.72
     backpack
    -0.71
    nina
    -0.71
    ход
    -0.69
    󠁥
    -0.69
    POSITIVE LOGITS
    rolment
    0.83
     ihtiyaç
    0.77
     checks
    0.74
     verliert
    0.71
     eléctrico
    0.71
     współ
    0.71
     trở
    0.71
    Fondo
    0.71
    Extent
    0.68
     popraw
    0.67
    Activations Density 0.025%

    No Known Activations