© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113156
    Prev
    Next
    INDEX
    Explanations

    Eureka, Eure [tent, tv show, names]

    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_10/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
    ться
    -3.00
    стойчи
    -2.78
     erwähnten
    -2.70
     tuttavia
    -2.63
    
    -2.48
     But
    -2.47
    檮
    -2.47
    .
    -2.38
     to
    -2.38
     ursprünglichen
    -2.36
    POSITIVE LOGITS
    .
    3.84
     atrav
    2.25
    咦
    2.22
     バッジ
    2.17
     Winners
    2.16
    ”
    2.11
     Aviso
    2.09
     بنات
    2.08
     Universo
    2.06
     tekst
    2.05
    Activations Density 0.001%

    No Known Activations