© 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. 102695
    Prev
    Next
    INDEX
    Explanations

    words starting with ba

    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
    写真は
    -0.93
     szczegól
    -0.88
    を
    -0.88
     catered
    -0.83
     conforming
    -0.70
     моя
    -0.69
    もあり
    -0.68
    なので
    -0.68
     weiße
    -0.68
     время
    -0.68
    POSITIVE LOGITS
    (^_^
    1.12
    為に
    0.98
     BUFFER
    0.96
    Ba
    0.96
     DialogInterface
    0.95
     IconData
    0.95
     Ba
    0.95
     ByteArray
    0.93
     basil
    0.92
    जू
    0.91
    Activations Density 0.019%

    No Known Activations